Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5132 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.6573. Min Act: -0.1700
Data Index: 3833111 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.3448. Min Act: -0.1700
Data Index: 8303134 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.3448. Min Act: -0.1700
Data Index: 2945466 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.1885. Min Act: -0.1700
Data Index: 5641348 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.1885. Min Act: -0.1700
Data Index: 1753637 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.1573. Min Act: -0.1700
Data Index: 6860611 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.1573. Min Act: -0.1700
Data Index: 804436 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.1260. Min Act: -0.1700
Data Index: 8248999 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.0948. Min Act: -0.1700
Data Index: 5249961 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6573. Min Range: -7.6573
Max Act: 7.0010. Min Act: -0.1700
Data Index: 8494356 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9698. Min Act: -0.1700
Data Index: 4009748 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9698. Min Act: -0.1700
Data Index: 8601350 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9698. Min Act: -0.1700
Data Index: 8602492 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9698. Min Act: -0.1700
Data Index: 5034737 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9385. Min Act: -0.1700
Data Index: 7505610 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9385. Min Act: -0.1700
Data Index: 3129536 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9385. Min Act: -0.1700
Data Index: 5442989 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9385. Min Act: -0.1700
Data Index: 149424 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9073. Min Act: -0.1700
Data Index: 1859343 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6573. Min Range: -7.6573
Max Act: 6.9073. Min Act: -0.1700
Data Index: 7175756 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19