Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 324 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4483. Min Act: -0.1700
Data Index: 7117341 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4483. Min Act: -0.1700
Data Index: 7623738 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4483. Min Act: -0.1700
Data Index: 1348383 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4326. Min Act: -0.1700
Data Index: 1512821 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4013. Min Act: -0.1700
Data Index: 8653068 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4013. Min Act: -0.1700
Data Index: 1289287 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4013. Min Act: -0.1700
Data Index: 8247627 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4170. Min Act: -0.1700
Data Index: 4909512 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4013. Min Act: -0.1700
Data Index: 5118188 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3856. Min Act: -0.1700
Data Index: 234521 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3856. Min Act: -0.1700
Data Index: 1269869 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.4013. Min Act: -0.1700
Data Index: 7253129 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3699. Min Act: -0.1700
Data Index: 1869916 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3072. Min Act: -0.1700
Data Index: 5000978 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3229. Min Act: -0.1700
Data Index: 429451 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3072. Min Act: -0.1700
Data Index: 5960423 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3229. Min Act: -0.1700
Data Index: 5288441 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3386. Min Act: -0.1700
Data Index: 485451 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3229. Min Act: -0.1700
Data Index: 2838156 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4483. Min Range: -3.4483
Max Act: 3.3386. Min Act: -0.1700
Data Index: 7053615 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19