Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1875 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.1983. Min Range: -12.1983
Max Act: 12.1358. Min Act: -0.1700
Data Index: 3544089 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1983. Min Range: -12.1983
Max Act: 12.1983. Min Act: -0.1700
Data Index: 5485027 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.0733. Min Act: -0.1700
Data Index: 2835550 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.4483. Min Act: -0.1700
Data Index: 4384636 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.3233. Min Act: -0.1700
Data Index: 4818313 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.3858. Min Act: -0.1700
Data Index: 7308808 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.1983. Min Act: -0.1700
Data Index: 4557480 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1983. Min Range: -12.1983
Max Act: 9.7608. Min Act: -0.1700
Data Index: 1257102 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.1358. Min Act: -0.1700
Data Index: 2941482 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.1983. Min Act: -0.1700
Data Index: 4493970 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.1358. Min Act: -0.1700
Data Index: 4582197 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.0733. Min Act: -0.1700
Data Index: 713640 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.2608. Min Act: -0.1700
Data Index: 2692086 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1983. Min Range: -12.1983
Max Act: 10.9483. Min Act: -0.1700
Data Index: 3908376 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1983. Min Range: -12.1983
Max Act: 10.9483. Min Act: -0.1700
Data Index: 7552438 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1983. Min Range: -12.1983
Max Act: 10.9483. Min Act: -0.1700
Data Index: 8509742 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1983. Min Range: -12.1983
Max Act: 11.0108. Min Act: -0.1700
Data Index: 243631 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1983. Min Range: -12.1983
Max Act: 10.8858. Min Act: -0.1700
Data Index: 5115197 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1983. Min Range: -12.1983
Max Act: 10.9483. Min Act: -0.1700
Data Index: 8801788 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1983. Min Range: -12.1983
Max Act: 10.8858. Min Act: -0.1700
Data Index: 3636510 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19