Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 109 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0533. Min Range: -2.0533
Max Act: 2.0533. Min Act: -0.1700
Data Index: 542732 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0533. Min Range: -2.0533
Max Act: 2.0196. Min Act: -0.1700
Data Index: 2263565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0533. Min Range: -2.0533
Max Act: 2.0196. Min Act: -0.1700
Data Index: 6695575 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9858. Min Act: -0.1700
Data Index: 8043953 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9689. Min Act: -0.1700
Data Index: 7742594 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9858. Min Act: -0.1700
Data Index: 6530111 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9689. Min Act: -0.1698
Data Index: 6845809 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9689. Min Act: -0.1700
Data Index: 5811372 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9519. Min Act: -0.1700
Data Index: 2209125 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9519. Min Act: -0.1700
Data Index: 3520555 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9519. Min Act: -0.1700
Data Index: 4282571 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9519. Min Act: -0.1700
Data Index: 6110232 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9519. Min Act: -0.1700
Data Index: 6055827 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9519. Min Act: -0.1700
Data Index: 5966399 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9689. Min Act: -0.1700
Data Index: 31378 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9349. Min Act: -0.1700
Data Index: 1804205 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9349. Min Act: -0.1700
Data Index: 6717303 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9349. Min Act: -0.1700
Data Index: 6041569 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9349. Min Act: -0.1700
Data Index: 6005600 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0533. Min Range: -2.0533
Max Act: 1.9519. Min Act: -0.1700
Data Index: 6808665 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19