Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.5867. Min Act: -0.1700
Data Index: 5435021 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.4617. Min Act: -0.1700
Data Index: 2244994 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.3367. Min Act: -0.1700
Data Index: 8566849 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.3367. Min Act: -0.1700
Data Index: 8019620 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.2742. Min Act: -0.1700
Data Index: 6421581 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.1492. Min Act: -0.1700
Data Index: 1792325 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.1492. Min Act: -0.1700
Data Index: 93884 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.0867. Min Act: -0.1700
Data Index: 7075621 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.0242. Min Act: -0.1700
Data Index: 7063800 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.0242. Min Act: -0.1700
Data Index: 5650340 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5867. Min Range: -8.5867
Max Act: 8.0242. Min Act: -0.1700
Data Index: 2458195 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.8367. Min Act: -0.1700
Data Index: 2830909 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.8367. Min Act: -0.1700
Data Index: 516431 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.8367. Min Act: -0.1700
Data Index: 4082220 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.7742. Min Act: -0.1700
Data Index: 6614542 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.7742. Min Act: -0.1700
Data Index: 4458960 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.7742. Min Act: -0.1700
Data Index: 6329 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.7742. Min Act: -0.1700
Data Index: 4464153 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.7742. Min Act: -0.1700
Data Index: 2839349 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5867. Min Range: -8.5867
Max Act: 7.6492. Min Act: -0.1700
Data Index: 2591082 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19