Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.5394. Min Act: -0.1700
Data Index: 604452 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.3207. Min Act: -0.1700
Data Index: 5577653 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.2582. Min Act: -0.1700
Data Index: 2225472 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.2582. Min Act: -0.1700
Data Index: 3529401 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.2269. Min Act: -0.1700
Data Index: 1888928 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.1332. Min Act: -0.1700
Data Index: 2225467 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.1644. Min Act: -0.1700
Data Index: 5763582 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.1019. Min Act: -0.1700
Data Index: 5965977 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.0394. Min Act: -0.1700
Data Index: 4772563 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.0707. Min Act: -0.1700
Data Index: 4484838 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5394. Min Range: -5.5394
Max Act: 5.0082. Min Act: -0.1700
Data Index: 1697156 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9769. Min Act: -0.1700
Data Index: 817485 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9457. Min Act: -0.1700
Data Index: 608780 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9457. Min Act: -0.1700
Data Index: 4779282 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9144. Min Act: -0.1700
Data Index: 3012575 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9457. Min Act: -0.1700
Data Index: 1022671 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9457. Min Act: -0.1700
Data Index: 8178818 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9144. Min Act: -0.1700
Data Index: 1749321 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9144. Min Act: -0.1700
Data Index: 872715 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5394. Min Range: -5.5394
Max Act: 4.9144. Min Act: -0.1700
Data Index: 4263485 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19