Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0987. Min Range: -8.0987
Max Act: 8.0987. Min Act: -0.1700
Data Index: 4923742 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0987. Min Range: -8.0987
Max Act: 8.0050. Min Act: -0.1700
Data Index: 2343202 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0987. Min Range: -8.0987
Max Act: 8.0050. Min Act: -0.1700
Data Index: 5421567 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.8800. Min Act: -0.1700
Data Index: 3683219 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.8800. Min Act: -0.1700
Data Index: 7373802 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.8487. Min Act: -0.1700
Data Index: 8675495 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.8175. Min Act: -0.1700
Data Index: 4863866 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.8175. Min Act: -0.1700
Data Index: 6721104 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.7550. Min Act: -0.1700
Data Index: 6144992 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.7550. Min Act: -0.1700
Data Index: 2056927 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.7550. Min Act: -0.1700
Data Index: 4933365 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.7237. Min Act: -0.1700
Data Index: 8638305 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.7237. Min Act: -0.1700
Data Index: 7212761 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.7237. Min Act: -0.1700
Data Index: 5072679 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.6300. Min Act: -0.1700
Data Index: 78601 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.6300. Min Act: -0.1700
Data Index: 8171587 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 7655767 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 6070745 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 2359327 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0987. Min Range: -8.0987
Max Act: 7.5987. Min Act: -0.1700
Data Index: 3432929 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19