Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4334 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1755. Min Act: -0.1700
Data Index: 2450802 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1442. Min Act: -0.1700
Data Index: 2755389 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1755. Min Range: -6.1755
Max Act: 6.1442. Min Act: -0.1700
Data Index: 1069179 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9567. Min Act: -0.1700
Data Index: 445993 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9567. Min Act: -0.1700
Data Index: 4456186 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.9255. Min Act: -0.1700
Data Index: 6577003 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8942. Min Act: -0.1700
Data Index: 3345013 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 7926969 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8317. Min Act: -0.1700
Data Index: 4030563 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8630. Min Act: -0.1700
Data Index: 7021435 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.8317. Min Act: -0.1700
Data Index: 4794859 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7692. Min Act: -0.1700
Data Index: 2450138 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 132301 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 8431544 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7692. Min Act: -0.1700
Data Index: 364208 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 5926836 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 143815 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 5622940 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 5157774 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1755. Min Range: -6.1755
Max Act: 5.7380. Min Act: -0.1700
Data Index: 6094295 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19