Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0557. Min Range: -5.0557
Max Act: 5.0557. Min Act: -0.1700
Data Index: 7964583 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 8202445 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 6841627 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8995. Min Act: -0.1700
Data Index: 8738631 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7745. Min Act: -0.1700
Data Index: 8044587 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7120. Min Act: -0.1700
Data Index: 1106230 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7432. Min Act: -0.1700
Data Index: 1965566 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.7120. Min Act: -0.1700
Data Index: 6609178 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.6807. Min Act: -0.1700
Data Index: 5601398 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.6807. Min Act: -0.1700
Data Index: 5609403 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.6807. Min Act: -0.1700
Data Index: 3578234 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.6495. Min Act: -0.1700
Data Index: 8561705 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.6495. Min Act: -0.1700
Data Index: 4061691 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.5870. Min Act: -0.1700
Data Index: 2619041 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.6182. Min Act: -0.1700
Data Index: 6781862 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.5870. Min Act: -0.1700
Data Index: 1112852 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.5870. Min Act: -0.1700
Data Index: 921709 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.5557. Min Act: -0.1700
Data Index: 1629224 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.5557. Min Act: -0.1700
Data Index: 4458179 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.5245. Min Act: -0.1700
Data Index: 1823656 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19