Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3310 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.5327. Min Act: -0.1700
Data Index: 637448 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.4390. Min Act: -0.1700
Data Index: 4340667 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.2202. Min Act: -0.1700
Data Index: 3554688 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.2202. Min Act: -0.1700
Data Index: 1412724 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.2515. Min Act: -0.1700
Data Index: 5687286 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0640. Min Act: -0.1700
Data Index: 3615305 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 7967751 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 8201452 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 781003 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 2536821 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 6653074 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0327. Min Act: -0.1700
Data Index: 2156752 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0015. Min Act: -0.1700
Data Index: 6653073 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0015. Min Act: -0.1700
Data Index: 8404684 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5327. Min Range: -7.5327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 5740309 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5327. Min Range: -7.5327
Max Act: 6.9702. Min Act: -0.1700
Data Index: 7268268 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5327. Min Range: -7.5327
Max Act: 7.0015. Min Act: -0.1700
Data Index: 4473616 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5327. Min Range: -7.5327
Max Act: 6.9702. Min Act: -0.1700
Data Index: 6067678 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5327. Min Range: -7.5327
Max Act: 6.9390. Min Act: -0.1700
Data Index: 2536822 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5327. Min Range: -7.5327
Max Act: 6.9077. Min Act: -0.1700
Data Index: 6544687 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19