Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6340 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.6366. Min Act: -0.1700
Data Index: 619087 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.3553. Min Act: -0.1700
Data Index: 4831253 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.2303. Min Act: -0.1700
Data Index: 5889489 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.1366. Min Act: -0.1700
Data Index: 7789878 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.1366. Min Act: -0.1700
Data Index: 1223163 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.0741. Min Act: -0.1700
Data Index: 8379849 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.1053. Min Act: -0.1700
Data Index: 5439080 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.0741. Min Act: -0.1700
Data Index: 7560259 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6366. Min Range: -7.6366
Max Act: 7.0116. Min Act: -0.1700
Data Index: 5030538 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.9803. Min Act: -0.1700
Data Index: 2828883 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.9803. Min Act: -0.1700
Data Index: 1397148 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.9491. Min Act: -0.1700
Data Index: 100896 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.8866. Min Act: -0.1700
Data Index: 4886774 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.9178. Min Act: -0.1700
Data Index: 397289 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.9178. Min Act: -0.1700
Data Index: 60775 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.8866. Min Act: -0.1700
Data Index: 4296395 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.8866. Min Act: -0.1700
Data Index: 3117851 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.8866. Min Act: -0.1700
Data Index: 4971686 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.8553. Min Act: -0.1700
Data Index: 2099786 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6366. Min Range: -7.6366
Max Act: 6.8553. Min Act: -0.1700
Data Index: 2725218 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19