Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.8336. Min Act: -0.1700
Data Index: 5990636 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.7711. Min Act: -0.1700
Data Index: 4776437 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.7086. Min Act: -0.1700
Data Index: 7185351 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.6461. Min Act: -0.1700
Data Index: 605837 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.5836. Min Act: -0.1700
Data Index: 6995784 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.5211. Min Act: -0.1700
Data Index: 5358901 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.5836. Min Act: -0.1700
Data Index: 8792424 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.4586. Min Act: -0.1700
Data Index: 8527521 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.4586. Min Act: -0.1700
Data Index: 514290 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.4586. Min Act: -0.1700
Data Index: 7011089 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.4586. Min Act: -0.1700
Data Index: 695206 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.4586. Min Act: -0.1700
Data Index: 6119662 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.4586. Min Act: -0.1700
Data Index: 4059151 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.3961. Min Act: -0.1700
Data Index: 5064414 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.3961. Min Act: -0.1700
Data Index: 6330403 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.3961. Min Act: -0.1700
Data Index: 695212 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.3961. Min Act: -0.1700
Data Index: 341376 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.3961. Min Act: -0.1700
Data Index: 695211 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.3336. Min Act: -0.1700
Data Index: 6785809 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8336. Min Range: -8.8336
Max Act: 8.2711. Min Act: -0.1700
Data Index: 104558 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19