Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1320 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.9817. Min Act: -0.1700
Data Index: 4379172 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.7317. Min Act: -0.1700
Data Index: 4156991 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.6692. Min Act: -0.1700
Data Index: 7303788 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.6692. Min Act: -0.1700
Data Index: 2583584 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.5129. Min Act: -0.1700
Data Index: 7888244 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.4192. Min Act: -0.1700
Data Index: 1424636 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.4192. Min Act: -0.1700
Data Index: 4017729 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.3879. Min Act: -0.1700
Data Index: 6251700 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.3879. Min Act: -0.1700
Data Index: 1906245 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.4192. Min Act: -0.1700
Data Index: 2385440 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.3567. Min Act: -0.1700
Data Index: 381950 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.3254. Min Act: -0.1700
Data Index: 3004074 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.3567. Min Act: -0.1700
Data Index: 2833384 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.3254. Min Act: -0.1700
Data Index: 124867 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.3254. Min Act: -0.1700
Data Index: 3829158 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.2942. Min Act: -0.1700
Data Index: 3583419 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.2629. Min Act: -0.1700
Data Index: 1259818 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.2629. Min Act: -0.1700
Data Index: 1843433 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.2317. Min Act: -0.1700
Data Index: 3415804 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9817. Min Range: -7.9817
Max Act: 7.2317. Min Act: -0.1700
Data Index: 398972 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19