Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1757. Min Range: -7.1757
Max Act: 7.1757. Min Act: -0.1700
Data Index: 4387084 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.7382. Min Act: -0.1700
Data Index: 3700832 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6757. Min Act: -0.1700
Data Index: 5422016 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6757. Min Act: -0.1700
Data Index: 7202040 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6444. Min Act: -0.1700
Data Index: 3183730 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.6444. Min Act: -0.1700
Data Index: 123739 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5819. Min Act: -0.1700
Data Index: 4874194 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5507. Min Act: -0.1700
Data Index: 7613033 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.5507. Min Act: -0.1700
Data Index: 3445003 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.4882. Min Act: -0.1700
Data Index: 438462 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.4569. Min Act: -0.1700
Data Index: 6408252 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.3632. Min Act: -0.1700
Data Index: 2722185 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.3944. Min Act: -0.1700
Data Index: 6256195 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.3319. Min Act: -0.1700
Data Index: 5965775 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.3007. Min Act: -0.1700
Data Index: 1107421 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.2694. Min Act: -0.1700
Data Index: 4095900 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.2694. Min Act: -0.1700
Data Index: 5809822 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.2382. Min Act: -0.1700
Data Index: 4442942 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.2694. Min Act: -0.1700
Data Index: 4551113 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1757. Min Range: -7.1757
Max Act: 6.2382. Min Act: -0.1700
Data Index: 7786185 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19