Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2279 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.2678. Min Act: -0.1700
Data Index: 8115462 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.2366. Min Act: -0.1700
Data Index: 5603097 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.2053. Min Act: -0.1700
Data Index: 5144420 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.2053. Min Act: -0.1700
Data Index: 1110385 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.1428. Min Act: -0.1700
Data Index: 5767644 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.1116. Min Act: -0.1700
Data Index: 1192692 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.1116. Min Act: -0.1700
Data Index: 4402995 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.1116. Min Act: -0.1700
Data Index: 975749 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.1116. Min Act: -0.1700
Data Index: 4341240 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.1116. Min Act: -0.1700
Data Index: 5343967 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.1428. Min Act: -0.1700
Data Index: 884871 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.0491. Min Act: -0.1700
Data Index: 3949474 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.0491. Min Act: -0.1700
Data Index: 6343386 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.0491. Min Act: -0.1700
Data Index: 5594737 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.0178. Min Act: -0.1700
Data Index: 256055 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.0178. Min Act: -0.1700
Data Index: 4489273 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2678. Min Range: -5.2678
Max Act: 5.0178. Min Act: -0.1700
Data Index: 2491130 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2678. Min Range: -5.2678
Max Act: 4.9866. Min Act: -0.1700
Data Index: 8291636 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2678. Min Range: -5.2678
Max Act: 4.9866. Min Act: -0.1700
Data Index: 8355608 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2678. Min Range: -5.2678
Max Act: 4.9553. Min Act: -0.1700
Data Index: 4874968 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19