Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3438 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1308. Min Range: -4.1308
Max Act: 4.1308. Min Act: -0.1700
Data Index: 1081055 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1308. Min Range: -4.1308
Max Act: 4.0057. Min Act: -0.1700
Data Index: 4050019 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9745. Min Act: -0.1700
Data Index: 7335005 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9432. Min Act: -0.1700
Data Index: 3461294 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9120. Min Act: -0.1700
Data Index: 8765242 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9120. Min Act: -0.1700
Data Index: 620044 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9120. Min Act: -0.1700
Data Index: 5105528 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.9120. Min Act: -0.1700
Data Index: 4168457 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8807. Min Act: -0.1700
Data Index: 984077 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8807. Min Act: -0.1700
Data Index: 4410717 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8807. Min Act: -0.1700
Data Index: 4051603 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8338. Min Act: -0.1700
Data Index: 3436066 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8494. Min Act: -0.1700
Data Index: 1467564 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8338. Min Act: -0.1700
Data Index: 4490815 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.8338. Min Act: -0.1700
Data Index: 567928 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.7869. Min Act: -0.1700
Data Index: 8122570 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.7869. Min Act: -0.1700
Data Index: 7081135 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.7869. Min Act: -0.1700
Data Index: 3764343 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.7869. Min Act: -0.1700
Data Index: 5102180 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1308. Min Range: -4.1308
Max Act: 3.7712. Min Act: -0.1700
Data Index: 5246386 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19