Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0060. Min Range: -8.0060
Max Act: 8.0060. Min Act: -0.1700
Data Index: 3881842 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.7560. Min Act: -0.1700
Data Index: 104312 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.6935. Min Act: -0.1700
Data Index: 7866486 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.6935. Min Act: -0.1700
Data Index: 6165878 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5997. Min Act: -0.1700
Data Index: 1365419 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5997. Min Act: -0.1700
Data Index: 2784939 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5685. Min Act: -0.1700
Data Index: 1005606 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5685. Min Act: -0.1700
Data Index: 8161083 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5685. Min Act: -0.1700
Data Index: 3690756 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5372. Min Act: -0.1700
Data Index: 2042092 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5372. Min Act: -0.1700
Data Index: 3298216 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5372. Min Act: -0.1700
Data Index: 1226678 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 7876490 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 6474165 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 1817662 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.5060. Min Act: -0.1700
Data Index: 4290930 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.4747. Min Act: -0.1700
Data Index: 6019539 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.4747. Min Act: -0.1700
Data Index: 4905674 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.4747. Min Act: -0.1700
Data Index: 8240210 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0060. Min Range: -8.0060
Max Act: 7.4747. Min Act: -0.1700
Data Index: 7502911 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19