Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1604 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4334. Min Range: -9.4334
Max Act: 9.4334. Min Act: -0.1700
Data Index: 815420 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4334. Min Range: -9.4334
Max Act: 9.2459. Min Act: -0.1700
Data Index: 3424088 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4334. Min Range: -9.4334
Max Act: 9.2459. Min Act: -0.1700
Data Index: 4849991 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4334. Min Range: -9.4334
Max Act: 9.1209. Min Act: -0.1700
Data Index: 2617485 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.9959. Min Act: -0.1700
Data Index: 8779782 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4334. Min Range: -9.4334
Max Act: 9.1209. Min Act: -0.1700
Data Index: 7845755 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4334. Min Range: -9.4334
Max Act: 9.0584. Min Act: -0.1700
Data Index: 5818981 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.9959. Min Act: -0.1700
Data Index: 5744142 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.8709. Min Act: -0.1700
Data Index: 815416 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.8709. Min Act: -0.1700
Data Index: 3937644 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.8709. Min Act: -0.1700
Data Index: 6892070 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.7459. Min Act: -0.1700
Data Index: 1530153 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.8084. Min Act: -0.1700
Data Index: 1900724 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.8084. Min Act: -0.1700
Data Index: 1121759 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.7459. Min Act: -0.1700
Data Index: 6336933 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.8084. Min Act: -0.1700
Data Index: 5154297 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.8084. Min Act: -0.1700
Data Index: 6721427 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.7459. Min Act: -0.1700
Data Index: 3214088 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.6834. Min Act: -0.1700
Data Index: 6467953 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4334. Min Range: -9.4334
Max Act: 8.6834. Min Act: -0.1700
Data Index: 4245424 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19