Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.6288. Min Act: -0.1700
Data Index: 1613386 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5662. Min Act: -0.1700
Data Index: 3249608 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5662. Min Act: -0.1700
Data Index: 3768873 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5193. Min Act: -0.1700
Data Index: 3815643 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5193. Min Act: -0.1700
Data Index: 2717191 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5036. Min Act: -0.1700
Data Index: 4452678 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5193. Min Act: -0.1700
Data Index: 466824 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5193. Min Act: -0.1700
Data Index: 7270256 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5036. Min Act: -0.1700
Data Index: 4982046 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5036. Min Act: -0.1700
Data Index: 532620 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4879. Min Act: -0.1700
Data Index: 1025852 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.5036. Min Act: -0.1700
Data Index: 4213232 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4879. Min Act: -0.1700
Data Index: 138234 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4566. Min Act: -0.1700
Data Index: 6841013 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4566. Min Act: -0.1700
Data Index: 1223243 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4723. Min Act: -0.1700
Data Index: 5176066 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4566. Min Act: -0.1700
Data Index: 77949 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4409. Min Act: -0.1700
Data Index: 1802859 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4566. Min Act: -0.1700
Data Index: 1041121 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6288. Min Range: -3.6288
Max Act: 3.4566. Min Act: -0.1700
Data Index: 822714 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19