Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7286. Min Range: -7.7286
Max Act: 7.7286. Min Act: -0.1700
Data Index: 5258166 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7286. Min Range: -7.7286
Max Act: 7.4161. Min Act: -0.1700
Data Index: 8221984 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7286. Min Range: -7.7286
Max Act: 7.3848. Min Act: -0.1700
Data Index: 123495 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7286. Min Range: -7.7286
Max Act: 7.1973. Min Act: -0.1700
Data Index: 3609512 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7286. Min Range: -7.7286
Max Act: 7.1348. Min Act: -0.1700
Data Index: 345198 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7286. Min Range: -7.7286
Max Act: 7.0411. Min Act: -0.1700
Data Index: 942981 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7286. Min Range: -7.7286
Max Act: 7.0098. Min Act: -0.1700
Data Index: 3121655 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.9786. Min Act: -0.1700
Data Index: 3278321 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.9786. Min Act: -0.1700
Data Index: 5323883 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.9161. Min Act: -0.1700
Data Index: 2748952 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.9161. Min Act: -0.1700
Data Index: 2300670 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.8848. Min Act: -0.1700
Data Index: 6636819 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.9161. Min Act: -0.1700
Data Index: 6104552 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.9161. Min Act: -0.1700
Data Index: 3005668 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.8848. Min Act: -0.1700
Data Index: 6204311 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.9161. Min Act: -0.1700
Data Index: 2748976 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.8848. Min Act: -0.1700
Data Index: 1387609 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.8536. Min Act: -0.1700
Data Index: 6091668 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.8223. Min Act: -0.1700
Data Index: 5562317 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7286. Min Range: -7.7286
Max Act: 6.8536. Min Act: -0.1700
Data Index: 2085805 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19