Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7179. Min Range: -9.7179
Max Act: 9.7179. Min Act: -0.1700
Data Index: 8263519 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7179. Min Range: -9.7179
Max Act: 9.6554. Min Act: -0.1700
Data Index: 6137448 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7179. Min Range: -9.7179
Max Act: 9.2804. Min Act: -0.1700
Data Index: 447366 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7179. Min Range: -9.7179
Max Act: 9.0929. Min Act: -0.1700
Data Index: 382560 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7179. Min Range: -9.7179
Max Act: 9.0304. Min Act: -0.1700
Data Index: 4563130 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.7179. Min Act: -0.1700
Data Index: 2675179 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.7179. Min Act: -0.1700
Data Index: 3796834 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.7179. Min Act: -0.1700
Data Index: 5445714 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.7179. Min Act: -0.1700
Data Index: 3514544 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.7179. Min Act: -0.1700
Data Index: 5696820 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.6554. Min Act: -0.1700
Data Index: 525768 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.6554. Min Act: -0.1700
Data Index: 6794674 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.6554. Min Act: -0.1700
Data Index: 1859144 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.5929. Min Act: -0.1700
Data Index: 7803093 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.5929. Min Act: -0.1700
Data Index: 5504957 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.4679. Min Act: -0.1700
Data Index: 2905264 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.4679. Min Act: -0.1700
Data Index: 6094810 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.4679. Min Act: -0.1700
Data Index: 6863191 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.4054. Min Act: -0.1700
Data Index: 6447414 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7179. Min Range: -9.7179
Max Act: 8.3429. Min Act: -0.1700
Data Index: 5226375 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19