Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.6801. Min Act: -0.1700
Data Index: 6367637 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5864. Min Act: -0.1700
Data Index: 2272947 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5864. Min Act: -0.1700
Data Index: 1889694 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5864. Min Act: -0.1700
Data Index: 8524346 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5864. Min Act: -0.1700
Data Index: 4680912 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5864. Min Act: -0.1700
Data Index: 4229518 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5239. Min Act: -0.1700
Data Index: 5434736 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5551. Min Act: -0.1700
Data Index: 1354688 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.5551. Min Act: -0.1700
Data Index: 5016477 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4926. Min Act: -0.1700
Data Index: 352326 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4614. Min Act: -0.1700
Data Index: 6228847 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4614. Min Act: -0.1700
Data Index: 1125325 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4614. Min Act: -0.1700
Data Index: 7859262 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4614. Min Act: -0.1700
Data Index: 1443199 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4301. Min Act: -0.1700
Data Index: 2740422 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4301. Min Act: -0.1700
Data Index: 8820052 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.4301. Min Act: -0.1700
Data Index: 3381174 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3676. Min Act: -0.1700
Data Index: 231182 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3989. Min Act: -0.1700
Data Index: 3590355 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6801. Min Range: -6.6801
Max Act: 6.3989. Min Act: -0.1700
Data Index: 1279871 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19