Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1736 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.4665. Min Act: -0.1700
Data Index: 2456087 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.3360. Min Act: -0.1700
Data Index: 625110 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.3031. Min Act: -0.1700
Data Index: 7644471 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.3031. Min Act: -0.1700
Data Index: 4760263 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.3031. Min Act: -0.1700
Data Index: 8426579 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2867. Min Act: -0.1700
Data Index: 1471118 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2702. Min Act: -0.1700
Data Index: 7499517 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2702. Min Act: -0.1700
Data Index: 3177931 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2702. Min Act: -0.1700
Data Index: 499738 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2537. Min Act: -0.1700
Data Index: 3625489 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2537. Min Act: -0.1700
Data Index: 1259810 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2371. Min Act: -0.1700
Data Index: 4947609 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2537. Min Act: -0.1700
Data Index: 7860785 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2371. Min Act: -0.1700
Data Index: 5492391 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2206. Min Act: -0.1700
Data Index: 6144857 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2371. Min Act: -0.1700
Data Index: 330294 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2371. Min Act: -0.1700
Data Index: 8077222 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2371. Min Act: -0.1700
Data Index: 1437761 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2206. Min Act: -0.1700
Data Index: 7021822 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4665. Min Range: -2.4665
Max Act: 2.2206. Min Act: -0.1700
Data Index: 272762 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19