Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.8114. Min Act: -0.1700
Data Index: 474376 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.4051. Min Act: -0.1700
Data Index: 1973214 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.2176. Min Act: -0.1700
Data Index: 2185955 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.2176. Min Act: -0.1700
Data Index: 8055618 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.1239. Min Act: -0.1700
Data Index: 3765210 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.1239. Min Act: -0.1700
Data Index: 5499574 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.0614. Min Act: -0.1700
Data Index: 8507661 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.0614. Min Act: -0.1700
Data Index: 854766 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.0301. Min Act: -0.1700
Data Index: 5833739 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8114. Min Range: -7.8114
Max Act: 7.0301. Min Act: -0.1700
Data Index: 8176535 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.9364. Min Act: -0.1700
Data Index: 7634121 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.9364. Min Act: -0.1700
Data Index: 5678051 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.8426. Min Act: -0.1700
Data Index: 7286557 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.8114. Min Act: -0.1700
Data Index: 65289 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.8114. Min Act: -0.1700
Data Index: 7911937 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.7801. Min Act: -0.1700
Data Index: 5819880 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.8426. Min Act: -0.1700
Data Index: 4466533 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.8426. Min Act: -0.1700
Data Index: 4890557 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.8114. Min Act: -0.1700
Data Index: 3881668 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8114. Min Range: -7.8114
Max Act: 6.7176. Min Act: -0.1700
Data Index: 5047219 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19