Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1790. Min Range: -8.1790
Max Act: 8.1790. Min Act: -0.1700
Data Index: 7640057 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1790. Min Range: -8.1790
Max Act: 8.1165. Min Act: -0.1700
Data Index: 5011330 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1790. Min Range: -8.1790
Max Act: 8.0540. Min Act: -0.1700
Data Index: 3435934 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1790. Min Range: -8.1790
Max Act: 8.0540. Min Act: -0.1700
Data Index: 6542929 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.9915. Min Act: -0.1700
Data Index: 6375106 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1790. Min Range: -8.1790
Max Act: 8.0227. Min Act: -0.1700
Data Index: 6214755 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.9915. Min Act: -0.1700
Data Index: 5235767 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.9602. Min Act: -0.1700
Data Index: 2916933 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.9602. Min Act: -0.1700
Data Index: 6991027 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.9290. Min Act: -0.1700
Data Index: 545447 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.8977. Min Act: -0.1700
Data Index: 7302721 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.8665. Min Act: -0.1700
Data Index: 2952281 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.8352. Min Act: -0.1700
Data Index: 4303525 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.8040. Min Act: -0.1700
Data Index: 1516702 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.8040. Min Act: -0.1700
Data Index: 3709824 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.7727. Min Act: -0.1700
Data Index: 5733876 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.7727. Min Act: -0.1700
Data Index: 8415042 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.7727. Min Act: -0.1700
Data Index: 1605763 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.7727. Min Act: -0.1700
Data Index: 5345089 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1790. Min Range: -8.1790
Max Act: 7.7727. Min Act: -0.1700
Data Index: 5651097 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19