Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4145 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.9305. Min Act: -0.1700
Data Index: 3787174 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.8054. Min Act: -0.1700
Data Index: 2002107 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.7741. Min Act: -0.1700
Data Index: 5575991 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.7585. Min Act: -0.1700
Data Index: 202217 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.7585. Min Act: -0.1700
Data Index: 7486273 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.7429. Min Act: -0.1700
Data Index: 3469363 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6803. Min Act: -0.1700
Data Index: 1336553 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6490. Min Act: -0.1700
Data Index: 5625854 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6334. Min Act: -0.1700
Data Index: 8607098 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6334. Min Act: -0.1700
Data Index: 413620 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6334. Min Act: -0.1700
Data Index: 6879368 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6177. Min Act: -0.1700
Data Index: 8160741 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6177. Min Act: -0.1700
Data Index: 7293848 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6177. Min Act: -0.1700
Data Index: 8781290 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6177. Min Act: -0.1700
Data Index: 5452513 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6021. Min Act: -0.1700
Data Index: 7973168 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6021. Min Act: -0.1700
Data Index: 2288437 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.5864. Min Act: -0.1700
Data Index: 7102829 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6021. Min Act: -0.1700
Data Index: 6879386 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9305. Min Range: -3.9305
Max Act: 3.6021. Min Act: -0.1700
Data Index: 4430305 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19