Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1580 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.8055. Min Act: -0.1700
Data Index: 6899885 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.4305. Min Act: -0.1700
Data Index: 6669073 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.3368. Min Act: -0.1700
Data Index: 3867515 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8796749 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.3055. Min Act: -0.1700
Data Index: 2197730 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.2743. Min Act: -0.1700
Data Index: 526692 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.2430. Min Act: -0.1700
Data Index: 637611 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.2118. Min Act: -0.1700
Data Index: 2016259 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.2118. Min Act: -0.1700
Data Index: 5106495 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.2118. Min Act: -0.1700
Data Index: 7072251 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.2118. Min Act: -0.1700
Data Index: 765447 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1493. Min Act: -0.1700
Data Index: 2978118 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1493. Min Act: -0.1700
Data Index: 3936697 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1493. Min Act: -0.1700
Data Index: 5113718 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1180. Min Act: -0.1700
Data Index: 3001446 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1493. Min Act: -0.1700
Data Index: 5767312 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1180. Min Act: -0.1700
Data Index: 7183783 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1180. Min Act: -0.1700
Data Index: 6761257 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1180. Min Act: -0.1700
Data Index: 8282495 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8055. Min Range: -5.8055
Max Act: 5.1180. Min Act: -0.1700
Data Index: 4374520 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19