Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 260 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.6464. Min Act: -0.1700
Data Index: 8642979 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.6151. Min Act: -0.1700
Data Index: 1574257 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.5526. Min Act: -0.1700
Data Index: 299537 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.4589. Min Act: -0.1700
Data Index: 4831831 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.4589. Min Act: -0.1700
Data Index: 4789382 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.3651. Min Act: -0.1700
Data Index: 4858414 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.3026. Min Act: -0.1700
Data Index: 3768581 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.2714. Min Act: -0.1700
Data Index: 4085243 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.2714. Min Act: -0.1700
Data Index: 7225716 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.2401. Min Act: -0.1700
Data Index: 3656650 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.2401. Min Act: -0.1700
Data Index: 665599 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.2401. Min Act: -0.1700
Data Index: 5810703 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.2088. Min Act: -0.1700
Data Index: 4755545 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.2088. Min Act: -0.1700
Data Index: 604813 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.1776. Min Act: -0.1700
Data Index: 2499787 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1995312 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.1151. Min Act: -0.1700
Data Index: 2921894 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.1463. Min Act: -0.1700
Data Index: 6830782 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.1463. Min Act: -0.1700
Data Index: 8253365 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6464. Min Range: -4.6464
Max Act: 4.1463. Min Act: -0.1700
Data Index: 1079705 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19