Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4792 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0475. Min Range: -6.0475
Max Act: 6.0475. Min Act: -0.1700
Data Index: 2303631 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.9538. Min Act: -0.1700
Data Index: 8408116 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.8600. Min Act: -0.1700
Data Index: 5842798 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.8913. Min Act: -0.1700
Data Index: 6752028 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.8288. Min Act: -0.1700
Data Index: 4268210 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.8288. Min Act: -0.1700
Data Index: 5326458 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.8288. Min Act: -0.1700
Data Index: 7973231 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7975. Min Act: -0.1700
Data Index: 767620 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7975. Min Act: -0.1700
Data Index: 7696328 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7975. Min Act: -0.1700
Data Index: 53537 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7663. Min Act: -0.1700
Data Index: 7531840 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7350. Min Act: -0.1700
Data Index: 3227110 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7350. Min Act: -0.1700
Data Index: 3304436 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7350. Min Act: -0.1700
Data Index: 4248151 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.7038. Min Act: -0.1700
Data Index: 7174121 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.6413. Min Act: -0.1700
Data Index: 3149798 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.6413. Min Act: -0.1700
Data Index: 4786343 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.6413. Min Act: -0.1700
Data Index: 3248526 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.6413. Min Act: -0.1700
Data Index: 7625846 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0475. Min Range: -6.0475
Max Act: 5.6100. Min Act: -0.1700
Data Index: 7982089 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19