Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2152. Min Range: -6.2152
Max Act: 6.1839. Min Act: -0.1700
Data Index: 6608847 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2152. Min Range: -6.2152
Max Act: 6.2152. Min Act: -0.1700
Data Index: 6994325 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2152. Min Range: -6.2152
Max Act: 6.1214. Min Act: -0.1700
Data Index: 3446727 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.9652. Min Act: -0.1700
Data Index: 7269417 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6716651 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.8089. Min Act: -0.1700
Data Index: 6874730 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.7464. Min Act: -0.1700
Data Index: 7269416 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.7152. Min Act: -0.1700
Data Index: 6369866 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.7464. Min Act: -0.1700
Data Index: 1148225 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.7152. Min Act: -0.1700
Data Index: 6874731 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.7152. Min Act: -0.1700
Data Index: 4885379 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.6527. Min Act: -0.1700
Data Index: 4735327 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.6527. Min Act: -0.1700
Data Index: 8116203 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.6214. Min Act: -0.1700
Data Index: 6608848 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.5589. Min Act: -0.1700
Data Index: 2783807 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.5902. Min Act: -0.1700
Data Index: 8430497 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.4964. Min Act: -0.1700
Data Index: 8551330 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.5277. Min Act: -0.1700
Data Index: 8012512 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.4964. Min Act: -0.1700
Data Index: 5854506 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2152. Min Range: -6.2152
Max Act: 5.4964. Min Act: -0.1700
Data Index: 126637 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19