Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2104 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2813. Min Range: -8.2813
Max Act: 8.2813. Min Act: -0.1700
Data Index: 3361479 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.8438. Min Act: -0.1700
Data Index: 6749761 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.7188. Min Act: -0.1700
Data Index: 5860547 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.7813. Min Act: -0.1700
Data Index: 5093329 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.7188. Min Act: -0.1700
Data Index: 4989045 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.6563. Min Act: -0.1700
Data Index: 2378548 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5938. Min Act: -0.1700
Data Index: 5860541 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5938. Min Act: -0.1700
Data Index: 8197758 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5938. Min Act: -0.1700
Data Index: 6945779 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5625. Min Act: -0.1700
Data Index: 8184185 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5625. Min Act: -0.1700
Data Index: 8734921 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5313. Min Act: -0.1700
Data Index: 2038958 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5313. Min Act: -0.1700
Data Index: 141923 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5313. Min Act: -0.1700
Data Index: 4964221 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5625. Min Act: -0.1700
Data Index: 3424232 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5000. Min Act: -0.1700
Data Index: 1168888 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5000. Min Act: -0.1700
Data Index: 5083812 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5000. Min Act: -0.1700
Data Index: 2729253 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.5000. Min Act: -0.1700
Data Index: 7075609 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2813. Min Range: -8.2813
Max Act: 7.4375. Min Act: -0.1700
Data Index: 2268766 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19