Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 782 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4792. Min Range: -9.4792
Max Act: 9.4792. Min Act: -0.1700
Data Index: 5670162 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4792. Min Range: -9.4792
Max Act: 9.2917. Min Act: -0.1700
Data Index: 3002899 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4792. Min Range: -9.4792
Max Act: 9.2292. Min Act: -0.1700
Data Index: 7888679 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4792. Min Range: -9.4792
Max Act: 9.1042. Min Act: -0.1700
Data Index: 831424 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4792. Min Range: -9.4792
Max Act: 9.0417. Min Act: -0.1700
Data Index: 1929610 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.9792. Min Act: -0.1700
Data Index: 3301134 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.9792. Min Act: -0.1700
Data Index: 1935371 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.9167. Min Act: -0.1700
Data Index: 5675389 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.9167. Min Act: -0.1700
Data Index: 8013711 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.9167. Min Act: -0.1700
Data Index: 6529870 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.8542. Min Act: -0.1700
Data Index: 3686886 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7917. Min Act: -0.1700
Data Index: 7449111 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7917. Min Act: -0.1700
Data Index: 1394106 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7917. Min Act: -0.1700
Data Index: 6392802 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7917. Min Act: -0.1700
Data Index: 1953567 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7917. Min Act: -0.1700
Data Index: 1802108 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7292. Min Act: -0.1700
Data Index: 3375981 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7917. Min Act: -0.1700
Data Index: 4145142 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.7917. Min Act: -0.1700
Data Index: 4672897 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4792. Min Range: -9.4792
Max Act: 8.8542. Min Act: -0.1700
Data Index: 2185151 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19