Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 845 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.8651. Min Act: -0.1700
Data Index: 895388 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.3963. Min Act: -0.1700
Data Index: 7370179 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.3651. Min Act: -0.1700
Data Index: 4697525 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.3963. Min Act: -0.1700
Data Index: 3557124 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.3026. Min Act: -0.1700
Data Index: 1496747 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.3026. Min Act: -0.1700
Data Index: 3570371 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.3026. Min Act: -0.1700
Data Index: 7209924 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.2713. Min Act: -0.1700
Data Index: 2382213 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.2401. Min Act: -0.1700
Data Index: 3168694 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.2088. Min Act: -0.1700
Data Index: 5889608 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.1776. Min Act: -0.1700
Data Index: 7788780 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.1776. Min Act: -0.1700
Data Index: 1302945 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.1776. Min Act: -0.1700
Data Index: 450044 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.1463. Min Act: -0.1700
Data Index: 3776386 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.1151. Min Act: -0.1700
Data Index: 5631384 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.1151. Min Act: -0.1700
Data Index: 4910433 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.0838. Min Act: -0.1700
Data Index: 7081788 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.0838. Min Act: -0.1700
Data Index: 2612566 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.0526. Min Act: -0.1700
Data Index: 2444881 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8651. Min Range: -5.8651
Max Act: 5.0838. Min Act: -0.1700
Data Index: 2671683 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19