Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1254. Min Range: -7.1254
Max Act: 7.1254. Min Act: -0.1700
Data Index: 8685062 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.5004. Min Act: -0.1700
Data Index: 2163485 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.4691. Min Act: -0.1700
Data Index: 4023522 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.4066. Min Act: -0.1700
Data Index: 3347020 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.3754. Min Act: -0.1700
Data Index: 8717154 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.3129. Min Act: -0.1700
Data Index: 6391884 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.3441. Min Act: -0.1700
Data Index: 3886413 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.3129. Min Act: -0.1700
Data Index: 8344974 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.2191. Min Act: -0.1700
Data Index: 5808843 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.2191. Min Act: -0.1700
Data Index: 4580930 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1879. Min Act: -0.1700
Data Index: 2895491 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1879. Min Act: -0.1700
Data Index: 4496644 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1879. Min Act: -0.1700
Data Index: 593702 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1566. Min Act: -0.1700
Data Index: 4370536 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1879. Min Act: -0.1700
Data Index: 2826247 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1566. Min Act: -0.1700
Data Index: 7580234 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1254. Min Act: -0.1700
Data Index: 2377805 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1254. Min Act: -0.1700
Data Index: 5772258 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.1254. Min Act: -0.1700
Data Index: 1311138 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1254. Min Range: -7.1254
Max Act: 6.0941. Min Act: -0.1700
Data Index: 4616427 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19