Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1507. Min Range: -7.1507
Max Act: 7.1507. Min Act: -0.1700
Data Index: 1411742 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1507. Min Range: -7.1507
Max Act: 7.1507. Min Act: -0.1700
Data Index: 1181712 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1507. Min Range: -7.1507
Max Act: 7.0882. Min Act: -0.1700
Data Index: 6936104 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.9632. Min Act: -0.1700
Data Index: 4713442 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.9319. Min Act: -0.1700
Data Index: 2418861 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.9007. Min Act: -0.1700
Data Index: 6294821 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8694. Min Act: -0.1700
Data Index: 1387777 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8382. Min Act: -0.1700
Data Index: 4754429 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8694. Min Act: -0.1700
Data Index: 3655801 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8694. Min Act: -0.1700
Data Index: 762370 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8382. Min Act: -0.1700
Data Index: 2461790 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8069. Min Act: -0.1700
Data Index: 2608550 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8069. Min Act: -0.1700
Data Index: 6919682 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8069. Min Act: -0.1700
Data Index: 4884056 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.8069. Min Act: -0.1700
Data Index: 3017796 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.7757. Min Act: -0.1700
Data Index: 2512803 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.7757. Min Act: -0.1700
Data Index: 7455738 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.7757. Min Act: -0.1700
Data Index: 1485177 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.7757. Min Act: -0.1700
Data Index: 7879971 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1507. Min Range: -7.1507
Max Act: 6.7757. Min Act: -0.1700
Data Index: 5428352 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19