Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6094 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.7075. Min Act: -0.1700
Data Index: 6838054 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.7232. Min Act: -0.1700
Data Index: 2410539 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.6136. Min Act: -0.1700
Data Index: 6672635 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5823. Min Act: -0.1700
Data Index: 5102406 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5667. Min Act: -0.1700
Data Index: 8725267 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5510. Min Act: -0.1700
Data Index: 339658 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5354. Min Act: -0.1700
Data Index: 3387589 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5197. Min Act: -0.1700
Data Index: 4305145 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5197. Min Act: -0.1700
Data Index: 7230502 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5041. Min Act: -0.1700
Data Index: 6547284 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5041. Min Act: -0.1700
Data Index: 3057173 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.5041. Min Act: -0.1700
Data Index: 5249642 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4884. Min Act: -0.1700
Data Index: 7878320 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4884. Min Act: -0.1700
Data Index: 7133935 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4727. Min Act: -0.1700
Data Index: 144585 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4884. Min Act: -0.1700
Data Index: 4819874 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4884. Min Act: -0.1700
Data Index: 1498988 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4727. Min Act: -0.1700
Data Index: 8649771 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4571. Min Act: -0.1700
Data Index: 8190488 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7232. Min Range: -3.7232
Max Act: 3.4571. Min Act: -0.1700
Data Index: 6982120 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19