Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3514. Min Range: -6.3514
Max Act: 6.3514. Min Act: -0.1700
Data Index: 12629 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3514. Min Range: -6.3514
Max Act: 6.1014. Min Act: -0.1700
Data Index: 3732116 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3514. Min Range: -6.3514
Max Act: 6.0076. Min Act: -0.1700
Data Index: 8548373 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3514. Min Range: -6.3514
Max Act: 6.0389. Min Act: -0.1700
Data Index: 2097449 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3514. Min Range: -6.3514
Max Act: 6.0076. Min Act: -0.1700
Data Index: 6874246 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.9139. Min Act: -0.1700
Data Index: 3823473 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.9451. Min Act: -0.1700
Data Index: 1018852 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.9139. Min Act: -0.1700
Data Index: 8616127 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.9139. Min Act: -0.1700
Data Index: 8577304 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.9139. Min Act: -0.1700
Data Index: 1969176 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8826. Min Act: -0.1700
Data Index: 1856564 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8826. Min Act: -0.1700
Data Index: 3207414 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8826. Min Act: -0.1700
Data Index: 4389955 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8826. Min Act: -0.1700
Data Index: 765275 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8514. Min Act: -0.1700
Data Index: 899385 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8514. Min Act: -0.1700
Data Index: 6491883 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8514. Min Act: -0.1700
Data Index: 987005 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8201. Min Act: -0.1700
Data Index: 661676 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8514. Min Act: -0.1700
Data Index: 3136858 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3514. Min Range: -6.3514
Max Act: 5.8514. Min Act: -0.1700
Data Index: 4095345 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19