Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1720 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6950. Min Act: -0.1700
Data Index: 3612898 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6950. Min Act: -0.1700
Data Index: 2144026 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6638. Min Act: -0.1700
Data Index: 1889117 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6638. Min Act: -0.1700
Data Index: 5012037 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6638. Min Act: -0.1700
Data Index: 3936875 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6325. Min Act: -0.1700
Data Index: 6701401 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6638. Min Act: -0.1700
Data Index: 7040668 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6325. Min Act: -0.1700
Data Index: 4445877 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6325. Min Act: -0.1700
Data Index: 6039386 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6325. Min Act: -0.1700
Data Index: 8358133 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2994345 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6325. Min Act: -0.1700
Data Index: 4026100 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6013. Min Act: -0.1700
Data Index: 3906659 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6013. Min Act: -0.1700
Data Index: 6084091 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6325. Min Act: -0.1700
Data Index: 4523613 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.5700. Min Act: -0.1700
Data Index: 5300046 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.5700. Min Act: -0.1700
Data Index: 106988 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.5700. Min Act: -0.1700
Data Index: 1243949 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.5700. Min Act: -0.1700
Data Index: 2094243 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6950. Min Range: -4.6950
Max Act: 4.6013. Min Act: -0.1700
Data Index: 2253231 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19