Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.9739. Min Act: -0.1700
Data Index: 7597395 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.9426. Min Act: -0.1700
Data Index: 13897 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.9426. Min Act: -0.1700
Data Index: 7108801 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.8176. Min Act: -0.1700
Data Index: 7864612 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.7551. Min Act: -0.1700
Data Index: 2618472 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.7239. Min Act: -0.1700
Data Index: 1198586 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.7239. Min Act: -0.1700
Data Index: 8595190 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.6926. Min Act: -0.1700
Data Index: 6191038 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.6926. Min Act: -0.1700
Data Index: 5371294 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.6926. Min Act: -0.1700
Data Index: 5220689 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.6614. Min Act: -0.1700
Data Index: 3533903 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1027781 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.6301. Min Act: -0.1700
Data Index: 5577422 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.5989. Min Act: -0.1700
Data Index: 6106151 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.6301. Min Act: -0.1700
Data Index: 389168 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.5989. Min Act: -0.1700
Data Index: 875764 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.5989. Min Act: -0.1700
Data Index: 696511 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.5989. Min Act: -0.1700
Data Index: 8086356 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.5989. Min Act: -0.1700
Data Index: 6281110 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9739. Min Range: -5.9739
Max Act: 5.5989. Min Act: -0.1700
Data Index: 4179706 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19