Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5437 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.4618. Min Act: -0.1700
Data Index: 6046932 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.4306. Min Act: -0.1700
Data Index: 5879853 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.3681. Min Act: -0.1700
Data Index: 3534510 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.3368. Min Act: -0.1700
Data Index: 2651500 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.2431. Min Act: -0.1700
Data Index: 7434258 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.1806. Min Act: -0.1700
Data Index: 4562246 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.1181. Min Act: -0.1700
Data Index: 908513 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0868. Min Act: -0.1700
Data Index: 2898416 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0556. Min Act: -0.1700
Data Index: 8800839 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0556. Min Act: -0.1700
Data Index: 3957041 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0556. Min Act: -0.1700
Data Index: 2396215 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0243. Min Act: -0.1700
Data Index: 1761329 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9931. Min Act: -0.1700
Data Index: 956600 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9306. Min Act: -0.1700
Data Index: 481588 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9306. Min Act: -0.1700
Data Index: 3323956 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9306. Min Act: -0.1700
Data Index: 38623 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9306. Min Act: -0.1700
Data Index: 2567976 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.8681. Min Act: -0.1700
Data Index: 3530572 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.8681. Min Act: -0.1700
Data Index: 3770281 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.8681. Min Act: -0.1700
Data Index: 1436839 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19