Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3881 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.3219. Min Act: -0.1700
Data Index: 3432679 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.3219. Min Act: -0.1700
Data Index: 3710565 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.3219. Min Act: -0.1700
Data Index: 2810695 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.1969. Min Act: -0.1700
Data Index: 6223637 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.1344. Min Act: -0.1700
Data Index: 8442960 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.1657. Min Act: -0.1700
Data Index: 1846697 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.1344. Min Act: -0.1700
Data Index: 314066 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.1344. Min Act: -0.1700
Data Index: 4047627 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.1032. Min Act: -0.1700
Data Index: 1813774 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.0719. Min Act: -0.1700
Data Index: 3451674 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.0407. Min Act: -0.1700
Data Index: 949848 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3219. Min Range: -7.3219
Max Act: 7.0094. Min Act: -0.1700
Data Index: 6763564 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.9782. Min Act: -0.1700
Data Index: 5588649 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.9469. Min Act: -0.1700
Data Index: 4953596 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.9157. Min Act: -0.1700
Data Index: 1701358 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.9469. Min Act: -0.1700
Data Index: 693628 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.9157. Min Act: -0.1700
Data Index: 3346982 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.8532. Min Act: -0.1700
Data Index: 1945510 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.8532. Min Act: -0.1700
Data Index: 6747232 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3219. Min Range: -7.3219
Max Act: 6.8532. Min Act: -0.1700
Data Index: 7599987 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19