Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4649 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0494. Min Range: -6.0494
Max Act: 6.0494. Min Act: -0.1700
Data Index: 2781444 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9556. Min Act: -0.1700
Data Index: 1704848 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 6200378 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9556. Min Act: -0.1700
Data Index: 6200375 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 2796548 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 7011748 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.8306. Min Act: -0.1700
Data Index: 6672671 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.7994. Min Act: -0.1700
Data Index: 2747192 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.7369. Min Act: -0.1700
Data Index: 4980927 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.7681. Min Act: -0.1700
Data Index: 965336 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.7369. Min Act: -0.1700
Data Index: 4969424 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.7056. Min Act: -0.1700
Data Index: 6762233 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.6744. Min Act: -0.1700
Data Index: 7358577 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.6744. Min Act: -0.1700
Data Index: 8658059 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.6744. Min Act: -0.1700
Data Index: 1261005 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.6431. Min Act: -0.1700
Data Index: 3731495 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.6431. Min Act: -0.1700
Data Index: 6538260 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.6119. Min Act: -0.1700
Data Index: 574062 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.5806. Min Act: -0.1700
Data Index: 2273726 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0494. Min Range: -6.0494
Max Act: 5.6119. Min Act: -0.1700
Data Index: 6467247 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19