Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3013 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.3448. Min Act: -0.1700
Data Index: 6249259 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.2820. Min Act: -0.1700
Data Index: 3965543 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.1877. Min Act: -0.1700
Data Index: 3265334 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.1562. Min Act: -0.1700
Data Index: 8794794 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.1405. Min Act: -0.1700
Data Index: 549141 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.1247. Min Act: -0.1700
Data Index: 6931760 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.1247. Min Act: -0.1700
Data Index: 8023172 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0932. Min Act: -0.1700
Data Index: 5587079 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0932. Min Act: -0.1700
Data Index: 5664474 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0774. Min Act: -0.1700
Data Index: 4396024 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0774. Min Act: -0.1700
Data Index: 3347144 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0617. Min Act: -0.1700
Data Index: 5345650 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0774. Min Act: -0.1700
Data Index: 8071734 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0617. Min Act: -0.1700
Data Index: 3965542 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0617. Min Act: -0.1700
Data Index: 2987354 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0459. Min Act: -0.1700
Data Index: 2230943 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0459. Min Act: -0.1700
Data Index: 5164027 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0459. Min Act: -0.1700
Data Index: 8114450 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0143. Min Act: -0.1700
Data Index: 3174674 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3448. Min Range: -3.3448
Max Act: 3.0143. Min Act: -0.1700
Data Index: 3786304 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19