Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 196 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0365. Min Range: -3.0365
Max Act: 3.0365. Min Act: -0.1700
Data Index: 8144506 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0365. Min Range: -3.0365
Max Act: 3.0049. Min Act: -0.1700
Data Index: 8547813 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9575. Min Act: -0.1700
Data Index: 6906301 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9733. Min Act: -0.1700
Data Index: 747008 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9575. Min Act: -0.1700
Data Index: 5142378 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9575. Min Act: -0.1700
Data Index: 1232478 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9417. Min Act: -0.1700
Data Index: 1254631 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9258. Min Act: -0.1700
Data Index: 6106725 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9100. Min Act: -0.1700
Data Index: 5546698 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9258. Min Act: -0.1700
Data Index: 5430994 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9100. Min Act: -0.1700
Data Index: 3678991 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.9100. Min Act: -0.1700
Data Index: 7009243 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8783. Min Act: -0.1700
Data Index: 722193 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8465. Min Act: -0.1700
Data Index: 6936281 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8465. Min Act: -0.1700
Data Index: 8017148 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8306. Min Act: -0.1700
Data Index: 6398660 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8306. Min Act: -0.1700
Data Index: 4362072 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8306. Min Act: -0.1700
Data Index: 7281759 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8306. Min Act: -0.1700
Data Index: 3275516 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0365. Min Range: -3.0365
Max Act: 2.8147. Min Act: -0.1700
Data Index: 3327593 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19