Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5204 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.6845. Min Act: -0.1700
Data Index: 6295207 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.4657. Min Act: -0.1700
Data Index: 1451363 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.4345. Min Act: -0.1700
Data Index: 7672817 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.3407. Min Act: -0.1700
Data Index: 3307364 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.3095. Min Act: -0.1700
Data Index: 8727206 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.2470. Min Act: -0.1700
Data Index: 8303420 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.2157. Min Act: -0.1700
Data Index: 8433496 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.2470. Min Act: -0.1700
Data Index: 2045814 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.2157. Min Act: -0.1700
Data Index: 5902841 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.1845. Min Act: -0.1700
Data Index: 1460153 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.1845. Min Act: -0.1700
Data Index: 8437395 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.1532. Min Act: -0.1700
Data Index: 3776447 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.1532. Min Act: -0.1700
Data Index: 174572 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.1532. Min Act: -0.1700
Data Index: 6362901 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.1220. Min Act: -0.1700
Data Index: 6199020 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.0907. Min Act: -0.1700
Data Index: 61897 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.0595. Min Act: -0.1700
Data Index: 3249855 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.0907. Min Act: -0.1700
Data Index: 1979114 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.0907. Min Act: -0.1700
Data Index: 5080929 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6845. Min Range: -6.6845
Max Act: 6.0907. Min Act: -0.1700
Data Index: 7966190 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19