Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2560 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2490. Min Range: -6.2490
Max Act: 6.2490. Min Act: -0.1700
Data Index: 7887206 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2490. Min Range: -6.2490
Max Act: 6.1240. Min Act: -0.1700
Data Index: 1609920 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2490. Min Range: -6.2490
Max Act: 6.0928. Min Act: -0.1700
Data Index: 3676022 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2490. Min Range: -6.2490
Max Act: 6.0615. Min Act: -0.1700
Data Index: 8368915 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.9990. Min Act: -0.1700
Data Index: 4455753 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.9053. Min Act: -0.1700
Data Index: 1201250 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.9365. Min Act: -0.1700
Data Index: 8582296 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.8740. Min Act: -0.1700
Data Index: 4890845 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.8428. Min Act: -0.1700
Data Index: 1214780 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.8740. Min Act: -0.1700
Data Index: 1562878 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.8115. Min Act: -0.1700
Data Index: 6625804 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.7490. Min Act: -0.1700
Data Index: 7299099 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.7490. Min Act: -0.1700
Data Index: 1324227 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.7490. Min Act: -0.1700
Data Index: 1753304 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.7178. Min Act: -0.1700
Data Index: 4986314 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.7178. Min Act: -0.1700
Data Index: 4330105 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.7178. Min Act: -0.1700
Data Index: 5758999 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.6865. Min Act: -0.1700
Data Index: 7862074 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.6553. Min Act: -0.1700
Data Index: 7534933 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2490. Min Range: -6.2490
Max Act: 5.6553. Min Act: -0.1700
Data Index: 3039787 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19