Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.6013. Min Act: -0.1700
Data Index: 2756758 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.5700. Min Act: -0.1700
Data Index: 6143382 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.4763. Min Act: -0.1700
Data Index: 3542574 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.4138. Min Act: -0.1700
Data Index: 1996547 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.3825. Min Act: -0.1700
Data Index: 82229 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.2888. Min Act: -0.1700
Data Index: 4904054 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.1950. Min Act: -0.1700
Data Index: 2634385 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.1638. Min Act: -0.1700
Data Index: 4720981 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.1013. Min Act: -0.1700
Data Index: 8460795 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.1325. Min Act: -0.1700
Data Index: 3806464 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.1325. Min Act: -0.1700
Data Index: 6043372 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.1013. Min Act: -0.1700
Data Index: 595489 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.0700. Min Act: -0.1700
Data Index: 8565317 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.0700. Min Act: -0.1700
Data Index: 6435857 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.1013. Min Act: -0.1700
Data Index: 6497121 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.0388. Min Act: -0.1700
Data Index: 3480120 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.0388. Min Act: -0.1700
Data Index: 2099193 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.0388. Min Act: -0.1700
Data Index: 2098522 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.0700. Min Act: -0.1700
Data Index: 4617361 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6013. Min Range: -6.6013
Max Act: 6.0388. Min Act: -0.1700
Data Index: 3806466 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19