Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.8568. Min Act: -0.1700
Data Index: 8038867 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.6380. Min Act: -0.1700
Data Index: 129272 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5443. Min Act: -0.1700
Data Index: 7773704 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5443. Min Act: -0.1700
Data Index: 5787988 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5130. Min Act: -0.1700
Data Index: 7773703 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5130. Min Act: -0.1700
Data Index: 5448269 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5443. Min Act: -0.1700
Data Index: 4785283 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.5130. Min Act: -0.1700
Data Index: 7706300 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4818. Min Act: -0.1700
Data Index: 3903984 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4505. Min Act: -0.1700
Data Index: 396782 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4193. Min Act: -0.1700
Data Index: 861312 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4193. Min Act: -0.1700
Data Index: 4523814 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3880. Min Act: -0.1700
Data Index: 6150646 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3880. Min Act: -0.1700
Data Index: 3807341 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3880. Min Act: -0.1700
Data Index: 7996457 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4193. Min Act: -0.1700
Data Index: 5630523 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.4193. Min Act: -0.1700
Data Index: 7668063 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3568. Min Act: -0.1700
Data Index: 1751694 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3568. Min Act: -0.1700
Data Index: 794296 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8568. Min Range: -5.8568
Max Act: 5.3568. Min Act: -0.1700
Data Index: 2686629 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19