Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4995 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3475. Min Range: -7.3475
Max Act: 7.3475. Min Act: -0.1700
Data Index: 190296 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3475. Min Range: -7.3475
Max Act: 7.0350. Min Act: -0.1700
Data Index: 3069792 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.9413. Min Act: -0.1700
Data Index: 4296195 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.9100. Min Act: -0.1700
Data Index: 8115103 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.8475. Min Act: -0.1700
Data Index: 7328114 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.8475. Min Act: -0.1700
Data Index: 1877733 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.8475. Min Act: -0.1700
Data Index: 7223381 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.8475. Min Act: -0.1700
Data Index: 2715327 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.8163. Min Act: -0.1700
Data Index: 7740382 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.8163. Min Act: -0.1700
Data Index: 441057 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7850. Min Act: -0.1700
Data Index: 7006461 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7850. Min Act: -0.1700
Data Index: 4946794 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7850. Min Act: -0.1700
Data Index: 6990508 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7538. Min Act: -0.1700
Data Index: 5709057 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7225. Min Act: -0.1700
Data Index: 6391701 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7225. Min Act: -0.1700
Data Index: 8093641 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7225. Min Act: -0.1700
Data Index: 398723 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7538. Min Act: -0.1700
Data Index: 7409530 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.7538. Min Act: -0.1700
Data Index: 2302966 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3475. Min Range: -7.3475
Max Act: 6.6913. Min Act: -0.1700
Data Index: 3341704 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19