Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.9583. Min Act: -0.1700
Data Index: 8471602 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.8020. Min Act: -0.1700
Data Index: 1170118 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.7395. Min Act: -0.1700
Data Index: 6377439 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.7083. Min Act: -0.1700
Data Index: 2172430 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.7083. Min Act: -0.1700
Data Index: 1658372 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.6770. Min Act: -0.1700
Data Index: 3405859 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.6770. Min Act: -0.1700
Data Index: 3639705 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.6770. Min Act: -0.1700
Data Index: 248207 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.6458. Min Act: -0.1700
Data Index: 1269407 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.5833. Min Act: -0.1700
Data Index: 3570775 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.5520. Min Act: -0.1700
Data Index: 730967 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.6145. Min Act: -0.1700
Data Index: 7929496 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.5520. Min Act: -0.1700
Data Index: 94516 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.5520. Min Act: -0.1700
Data Index: 5838294 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.5520. Min Act: -0.1700
Data Index: 1111692 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.5208. Min Act: -0.1700
Data Index: 4932020 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.4895. Min Act: -0.1700
Data Index: 6445248 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.4895. Min Act: -0.1700
Data Index: 8095692 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.5208. Min Act: -0.1700
Data Index: 2140440 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9583. Min Range: -6.9583
Max Act: 6.4895. Min Act: -0.1700
Data Index: 5100845 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19