Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1321. Min Range: -6.1321
Max Act: 6.1321. Min Act: -0.1700
Data Index: 5141488 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.8508. Min Act: -0.1700
Data Index: 6620833 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.7883. Min Act: -0.1700
Data Index: 5588691 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.7883. Min Act: -0.1700
Data Index: 5139468 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.7883. Min Act: -0.1700
Data Index: 2683795 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.7571. Min Act: -0.1700
Data Index: 189211 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.7258. Min Act: -0.1700
Data Index: 8363899 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.7258. Min Act: -0.1700
Data Index: 3581659 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.7258. Min Act: -0.1700
Data Index: 5951885 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6946. Min Act: -0.1700
Data Index: 8519073 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6946. Min Act: -0.1700
Data Index: 8160731 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6946. Min Act: -0.1700
Data Index: 184047 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6633. Min Act: -0.1700
Data Index: 2221346 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6633. Min Act: -0.1700
Data Index: 587423 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6321. Min Act: -0.1700
Data Index: 5861965 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6321. Min Act: -0.1700
Data Index: 1339265 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6321. Min Act: -0.1700
Data Index: 8716055 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6008. Min Act: -0.1700
Data Index: 7614595 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6008. Min Act: -0.1700
Data Index: 380103 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1321. Min Range: -6.1321
Max Act: 5.6008. Min Act: -0.1700
Data Index: 5623731 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19