Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3976 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.4185. Min Act: -0.1700
Data Index: 909108 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.3873. Min Act: -0.1700
Data Index: 8687108 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.3560. Min Act: -0.1700
Data Index: 142001 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.3560. Min Act: -0.1700
Data Index: 5218171 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.3248. Min Act: -0.1700
Data Index: 3426569 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.2310. Min Act: -0.1700
Data Index: 442265 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.2623. Min Act: -0.1700
Data Index: 7565024 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.2310. Min Act: -0.1700
Data Index: 2840594 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.2310. Min Act: -0.1700
Data Index: 2262413 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1998. Min Act: -0.1700
Data Index: 5862689 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1998. Min Act: -0.1700
Data Index: 3822911 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1998. Min Act: -0.1700
Data Index: 7390087 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1998. Min Act: -0.1700
Data Index: 4753643 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1685. Min Act: -0.1700
Data Index: 6240540 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1685. Min Act: -0.1700
Data Index: 1283740 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1685. Min Act: -0.1700
Data Index: 750438 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.1685. Min Act: -0.1700
Data Index: 4000618 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.0748. Min Act: -0.1700
Data Index: 7735926 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.0748. Min Act: -0.1700
Data Index: 8414698 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4185. Min Range: -6.4185
Max Act: 6.0748. Min Act: -0.1700
Data Index: 1641640 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19