Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2805 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.5429. Min Act: -0.1700
Data Index: 6245239 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.5429. Min Act: -0.1700
Data Index: 5504898 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.4803. Min Act: -0.1700
Data Index: 2371384 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.4489. Min Act: -0.1700
Data Index: 6809426 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.4803. Min Act: -0.1700
Data Index: 3596919 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.4176. Min Act: -0.1700
Data Index: 4968960 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.4333. Min Act: -0.1700
Data Index: 4888391 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.3862. Min Act: -0.1700
Data Index: 2371409 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.3392. Min Act: -0.1700
Data Index: 8502243 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.3235. Min Act: -0.1700
Data Index: 6466899 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2921. Min Act: -0.1700
Data Index: 6261965 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.3078. Min Act: -0.1700
Data Index: 2371391 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2764. Min Act: -0.1700
Data Index: 6979582 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2293. Min Act: -0.1700
Data Index: 8327243 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2450. Min Act: -0.1700
Data Index: 678979 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2450. Min Act: -0.1700
Data Index: 1549661 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.3078. Min Act: -0.1700
Data Index: 2371407 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2450. Min Act: -0.1700
Data Index: 6060531 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2293. Min Act: -0.1700
Data Index: 3462495 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5429. Min Range: -3.5429
Max Act: 3.2764. Min Act: -0.1700
Data Index: 2245804 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19