Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6387 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3271. Min Range: -9.3271
Max Act: 9.3271. Min Act: -0.1700
Data Index: 1367620 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3271. Min Range: -9.3271
Max Act: 9.1396. Min Act: -0.1700
Data Index: 3855963 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3271. Min Range: -9.3271
Max Act: 9.0771. Min Act: -0.1700
Data Index: 3737008 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3271. Min Range: -9.3271
Max Act: 9.0771. Min Act: -0.1700
Data Index: 6419716 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.9521. Min Act: -0.1700
Data Index: 7314690 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.8896. Min Act: -0.1700
Data Index: 6158376 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.8271. Min Act: -0.1700
Data Index: 1081522 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.7021. Min Act: -0.1700
Data Index: 908276 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.7021. Min Act: -0.1700
Data Index: 476778 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.7021. Min Act: -0.1700
Data Index: 689892 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.7021. Min Act: -0.1700
Data Index: 8548307 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.5771. Min Act: -0.1700
Data Index: 7860453 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.5771. Min Act: -0.1700
Data Index: 2348252 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.5771. Min Act: -0.1700
Data Index: 2445735 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.5146. Min Act: -0.1700
Data Index: 1379156 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.5146. Min Act: -0.1700
Data Index: 1069618 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.5146. Min Act: -0.1700
Data Index: 1442206 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.5146. Min Act: -0.1700
Data Index: 5690814 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.4521. Min Act: -0.1700
Data Index: 6705437 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3271. Min Range: -9.3271
Max Act: 8.4521. Min Act: -0.1700
Data Index: 4758738 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19