Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.1288. Min Act: -0.1700
Data Index: 5275767 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.1288. Min Act: -0.1700
Data Index: 2884201 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.0663. Min Act: -0.1700
Data Index: 6699400 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.0350. Min Act: -0.1700
Data Index: 2156422 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.0663. Min Act: -0.1700
Data Index: 1277248 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.0350. Min Act: -0.1700
Data Index: 8188594 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.0038. Min Act: -0.1700
Data Index: 8028692 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.9725. Min Act: -0.1700
Data Index: 3760980 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1288. Min Range: -7.1288
Max Act: 7.0038. Min Act: -0.1700
Data Index: 1655358 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.9725. Min Act: -0.1700
Data Index: 695834 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.9725. Min Act: -0.1700
Data Index: 2164389 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.9725. Min Act: -0.1700
Data Index: 1530453 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.9413. Min Act: -0.1700
Data Index: 8240494 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.8788. Min Act: -0.1700
Data Index: 8571924 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.8788. Min Act: -0.1700
Data Index: 7482767 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.8788. Min Act: -0.1700
Data Index: 5460277 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.8788. Min Act: -0.1700
Data Index: 7417113 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.8788. Min Act: -0.1700
Data Index: 2523731 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.8475. Min Act: -0.1700
Data Index: 8182497 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1288. Min Range: -7.1288
Max Act: 6.8475. Min Act: -0.1700
Data Index: 4212839 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19