Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2339 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.8018. Min Act: -0.1700
Data Index: 509014 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.8330. Min Act: -0.1700
Data Index: 2703246 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.8018. Min Act: -0.1700
Data Index: 509015 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.7393. Min Act: -0.1700
Data Index: 2703251 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.7393. Min Act: -0.1700
Data Index: 509016 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.6768. Min Act: -0.1700
Data Index: 2261853 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.5830. Min Act: -0.1700
Data Index: 6969337 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.4893. Min Act: -0.1700
Data Index: 4833195 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.5205. Min Act: -0.1700
Data Index: 2261852 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.5518. Min Act: -0.1700
Data Index: 4155474 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.5205. Min Act: -0.1700
Data Index: 6170561 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.5205. Min Act: -0.1700
Data Index: 8558960 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.4580. Min Act: -0.1700
Data Index: 8558961 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.4580. Min Act: -0.1700
Data Index: 4155466 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.4893. Min Act: -0.1700
Data Index: 7685688 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.5205. Min Act: -0.1700
Data Index: 5670388 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.4580. Min Act: -0.1700
Data Index: 4155473 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.4580. Min Act: -0.1700
Data Index: 6741342 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.4893. Min Act: -0.1700
Data Index: 7685682 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8330. Min Range: -5.8330
Max Act: 5.3955. Min Act: -0.1700
Data Index: 8139491 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19