Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0878. Min Range: -7.0878
Max Act: 7.0878. Min Act: -0.1700
Data Index: 2929552 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.9315. Min Act: -0.1700
Data Index: 1723136 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.8378. Min Act: -0.1700
Data Index: 5827611 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.7440. Min Act: -0.1700
Data Index: 1306375 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.7440. Min Act: -0.1700
Data Index: 7566658 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6503. Min Act: -0.1700
Data Index: 721105 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6815. Min Act: -0.1700
Data Index: 1287258 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6190. Min Act: -0.1700
Data Index: 3029474 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5878. Min Act: -0.1700
Data Index: 5071329 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5565. Min Act: -0.1700
Data Index: 7329130 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5253. Min Act: -0.1700
Data Index: 3756597 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4628. Min Act: -0.1700
Data Index: 7630885 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4628. Min Act: -0.1700
Data Index: 6894783 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4628. Min Act: -0.1700
Data Index: 3539747 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4315. Min Act: -0.1700
Data Index: 6770557 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4315. Min Act: -0.1700
Data Index: 2492761 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.4003. Min Act: -0.1700
Data Index: 7137429 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3690. Min Act: -0.1700
Data Index: 8608122 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3690. Min Act: -0.1700
Data Index: 3920856 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.3378. Min Act: -0.1700
Data Index: 5619574 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19