Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1014 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.2424. Min Act: -0.1700
Data Index: 2115118 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.1799. Min Act: -0.1700
Data Index: 5282353 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.1799. Min Act: -0.1700
Data Index: 8191180 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.1174. Min Act: -0.1700
Data Index: 8464369 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.0861. Min Act: -0.1700
Data Index: 4030668 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.0549. Min Act: -0.1700
Data Index: 4188563 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.0236. Min Act: -0.1700
Data Index: 2969435 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9924. Min Act: -0.1700
Data Index: 1999351 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.0236. Min Act: -0.1700
Data Index: 222793 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.0236. Min Act: -0.1700
Data Index: 2140405 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2424. Min Range: -5.2424
Max Act: 5.0236. Min Act: -0.1700
Data Index: 5126171 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9924. Min Act: -0.1700
Data Index: 7538554 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9924. Min Act: -0.1700
Data Index: 794018 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9611. Min Act: -0.1700
Data Index: 3557145 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9611. Min Act: -0.1700
Data Index: 5540036 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9299. Min Act: -0.1700
Data Index: 5870071 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9299. Min Act: -0.1700
Data Index: 2553172 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9299. Min Act: -0.1700
Data Index: 1594249 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.9299. Min Act: -0.1700
Data Index: 3337032 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2424. Min Range: -5.2424
Max Act: 4.8986. Min Act: -0.1700
Data Index: 6638548 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19