Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.5768. Min Act: -0.1700
Data Index: 3186743 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.5768. Min Act: -0.1700
Data Index: 8313691 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.4518. Min Act: -0.1700
Data Index: 5323274 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.4205. Min Act: -0.1700
Data Index: 8168903 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.3893. Min Act: -0.1700
Data Index: 3186738 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.3268. Min Act: -0.1700
Data Index: 7793729 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.3580. Min Act: -0.1700
Data Index: 2120173 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.2955. Min Act: -0.1700
Data Index: 7960595 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.2955. Min Act: -0.1700
Data Index: 2387960 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.2643. Min Act: -0.1700
Data Index: 6759996 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.2330. Min Act: -0.1700
Data Index: 7960602 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.2018. Min Act: -0.1700
Data Index: 5854566 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.2018. Min Act: -0.1700
Data Index: 5469515 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.1705. Min Act: -0.1700
Data Index: 3209059 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.2330. Min Act: -0.1700
Data Index: 5392887 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.1705. Min Act: -0.1700
Data Index: 2861581 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.1393. Min Act: -0.1700
Data Index: 4011755 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.1705. Min Act: -0.1700
Data Index: 3209060 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.1705. Min Act: -0.1700
Data Index: 4183082 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5768. Min Range: -6.5768
Max Act: 6.0768. Min Act: -0.1700
Data Index: 6449478 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19