Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3133 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3351. Min Range: -6.3351
Max Act: 6.3351. Min Act: -0.1700
Data Index: 5030560 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3351. Min Range: -6.3351
Max Act: 6.3039. Min Act: -0.1700
Data Index: 6297467 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3351. Min Range: -6.3351
Max Act: 6.2414. Min Act: -0.1700
Data Index: 1541938 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3351. Min Range: -6.3351
Max Act: 6.1789. Min Act: -0.1700
Data Index: 2448633 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3351. Min Range: -6.3351
Max Act: 6.0226. Min Act: -0.1700
Data Index: 1511185 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.9914. Min Act: -0.1700
Data Index: 3685894 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.9914. Min Act: -0.1700
Data Index: 8488043 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.9601. Min Act: -0.1700
Data Index: 3367807 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.9601. Min Act: -0.1700
Data Index: 3761340 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.8976. Min Act: -0.1700
Data Index: 6015598 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.8976. Min Act: -0.1700
Data Index: 1290769 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.8664. Min Act: -0.1700
Data Index: 508697 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.8976. Min Act: -0.1700
Data Index: 6469814 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.8351. Min Act: -0.1700
Data Index: 7294081 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.7414. Min Act: -0.1700
Data Index: 1683294 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.7101. Min Act: -0.1700
Data Index: 1502021 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.7101. Min Act: -0.1700
Data Index: 2495570 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.6476. Min Act: -0.1700
Data Index: 4393283 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.6476. Min Act: -0.1700
Data Index: 1933180 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3351. Min Range: -6.3351
Max Act: 5.6789. Min Act: -0.1700
Data Index: 1988636 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19