Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.3857. Min Act: -0.1700
Data Index: 7009705 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.3857. Min Act: -0.1700
Data Index: 5534865 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.3232. Min Act: -0.1700
Data Index: 3931388 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.3232. Min Act: -0.1700
Data Index: 3132282 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.2920. Min Act: -0.1700
Data Index: 7535176 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.2607. Min Act: -0.1700
Data Index: 7227160 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.2295. Min Act: -0.1700
Data Index: 8721648 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.0732. Min Act: -0.1700
Data Index: 7515880 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.0732. Min Act: -0.1700
Data Index: 551958 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.0732. Min Act: -0.1700
Data Index: 5440475 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.0419. Min Act: -0.1700
Data Index: 1198482 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3857. Min Range: -4.3857
Max Act: 4.0107. Min Act: -0.1700
Data Index: 2288665 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9481. Min Act: -0.1700
Data Index: 7561551 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9794. Min Act: -0.1700
Data Index: 8503922 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9794. Min Act: -0.1700
Data Index: 6931060 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9481. Min Act: -0.1700
Data Index: 7532149 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9481. Min Act: -0.1700
Data Index: 8152057 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9169. Min Act: -0.1700
Data Index: 6576831 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9481. Min Act: -0.1700
Data Index: 1646984 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3857. Min Range: -4.3857
Max Act: 3.9169. Min Act: -0.1700
Data Index: 5243698 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19