Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.5265. Min Act: -0.1700
Data Index: 7151056 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.4640. Min Act: -0.1700
Data Index: 7630652 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.4640. Min Act: -0.1700
Data Index: 7630639 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.4015. Min Act: -0.1700
Data Index: 8191795 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.3390. Min Act: -0.1700
Data Index: 2464863 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.3390. Min Act: -0.1700
Data Index: 5934532 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.3390. Min Act: -0.1700
Data Index: 6254750 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.3390. Min Act: -0.1700
Data Index: 7418263 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.3390. Min Act: -0.1696
Data Index: 7110132 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 2886375 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2765. Min Act: -0.1699
Data Index: 7151068 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 7899416 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 1166592 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 4475097 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 7151060 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 7151062 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.1515. Min Act: -0.1700
Data Index: 3560740 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 122373 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 6913338 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5265. Min Range: -8.5265
Max Act: 8.2140. Min Act: -0.1700
Data Index: 7151065 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19