Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5894 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.8756. Min Act: -0.1700
Data Index: 976891 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.8131. Min Act: -0.1700
Data Index: 963598 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.6568. Min Act: -0.1700
Data Index: 7412207 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.5318. Min Act: -0.1700
Data Index: 12159 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.5006. Min Act: -0.1700
Data Index: 4034541 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.5006. Min Act: -0.1700
Data Index: 4878442 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.5318. Min Act: -0.1700
Data Index: 7127843 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.4068. Min Act: -0.1700
Data Index: 1997306 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.3443. Min Act: -0.1700
Data Index: 4879718 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.3131. Min Act: -0.1700
Data Index: 1356591 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.3131. Min Act: -0.1700
Data Index: 3527646 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.2506. Min Act: -0.1700
Data Index: 891214 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.2193. Min Act: -0.1700
Data Index: 3543554 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.2193. Min Act: -0.1700
Data Index: 155088 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.2193. Min Act: -0.1700
Data Index: 6306281 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.1881. Min Act: -0.1700
Data Index: 8475227 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.1881. Min Act: -0.1700
Data Index: 818408 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.1881. Min Act: -0.1700
Data Index: 5183772 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.0943. Min Act: -0.1700
Data Index: 747411 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8756. Min Range: -6.8756
Max Act: 6.0943. Min Act: -0.1700
Data Index: 8669234 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19