Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.8152. Min Act: -0.1700
Data Index: 1116554 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.6589. Min Act: -0.1700
Data Index: 8523612 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.5339. Min Act: -0.1700
Data Index: 8499225 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.5027. Min Act: -0.1700
Data Index: 7351162 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.5027. Min Act: -0.1700
Data Index: 3276523 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.5339. Min Act: -0.1700
Data Index: 2350580 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.5027. Min Act: -0.1700
Data Index: 1950443 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.4714. Min Act: -0.1700
Data Index: 4001273 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.4402. Min Act: -0.1700
Data Index: 4290783 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.4089. Min Act: -0.1700
Data Index: 8176751 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.4089. Min Act: -0.1700
Data Index: 8333202 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.4402. Min Act: -0.1700
Data Index: 7591037 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.4089. Min Act: -0.1700
Data Index: 2674027 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.3777. Min Act: -0.1700
Data Index: 4830302 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.3777. Min Act: -0.1700
Data Index: 5811228 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.3777. Min Act: -0.1700
Data Index: 290172 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.3777. Min Act: -0.1700
Data Index: 7431986 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.3464. Min Act: -0.1700
Data Index: 6748049 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.3152. Min Act: -0.1700
Data Index: 6360970 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8152. Min Range: -5.8152
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2300258 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19