Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.9786. Min Act: -0.1700
Data Index: 6593215 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.8223. Min Act: -0.1700
Data Index: 1188225 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.5723. Min Act: -0.1700
Data Index: 1298984 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.5723. Min Act: -0.1700
Data Index: 5667109 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.5411. Min Act: -0.1700
Data Index: 8179486 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.4786. Min Act: -0.1700
Data Index: 3607226 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.4473. Min Act: -0.1700
Data Index: 4501421 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.4161. Min Act: -0.1700
Data Index: 2397055 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3848. Min Act: -0.1700
Data Index: 7080760 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3848. Min Act: -0.1700
Data Index: 898180 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3848. Min Act: -0.1700
Data Index: 123778 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3536. Min Act: -0.1700
Data Index: 5595200 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3536. Min Act: -0.1700
Data Index: 592391 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3223. Min Act: -0.1700
Data Index: 512426 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3223. Min Act: -0.1700
Data Index: 5360351 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3223. Min Act: -0.1700
Data Index: 7530953 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.3223. Min Act: -0.1700
Data Index: 650762 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.2911. Min Act: -0.1700
Data Index: 6473360 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.2911. Min Act: -0.1700
Data Index: 781127 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9786. Min Range: -5.9786
Max Act: 5.2911. Min Act: -0.1700
Data Index: 826411 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19