Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4392 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0573. Min Range: -8.0573
Max Act: 8.0573. Min Act: -0.1700
Data Index: 2003882 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.8698. Min Act: -0.1700
Data Index: 5323851 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.5260. Min Act: -0.1700
Data Index: 2044579 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.5260. Min Act: -0.1700
Data Index: 4773942 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.4948. Min Act: -0.1700
Data Index: 4448644 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.4948. Min Act: -0.1700
Data Index: 826940 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.4323. Min Act: -0.1700
Data Index: 5711078 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3698. Min Act: -0.1700
Data Index: 3957180 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3698. Min Act: -0.1700
Data Index: 1325907 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3698. Min Act: -0.1700
Data Index: 8282920 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3385. Min Act: -0.1700
Data Index: 8056481 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3385. Min Act: -0.1700
Data Index: 5119099 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3385. Min Act: -0.1700
Data Index: 7235545 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3385. Min Act: -0.1700
Data Index: 2392833 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3385. Min Act: -0.1700
Data Index: 5213351 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3073. Min Act: -0.1700
Data Index: 2451069 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.3073. Min Act: -0.1700
Data Index: 520852 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.2760. Min Act: -0.1700
Data Index: 6449272 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.2448. Min Act: -0.1700
Data Index: 1052655 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0573. Min Range: -8.0573
Max Act: 7.2448. Min Act: -0.1700
Data Index: 71019 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19