Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5624 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.8275. Min Act: -0.1700
Data Index: 543380 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.7338. Min Act: -0.1700
Data Index: 4776386 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.7338. Min Act: -0.1700
Data Index: 1036084 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.7338. Min Act: -0.1700
Data Index: 5397646 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6713. Min Act: -0.1700
Data Index: 5403967 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6713. Min Act: -0.1700
Data Index: 2423430 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6400. Min Act: -0.1700
Data Index: 548752 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6400. Min Act: -0.1700
Data Index: 6600668 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6713. Min Act: -0.1700
Data Index: 8448406 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6400. Min Act: -0.1700
Data Index: 1335921 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6400. Min Act: -0.1700
Data Index: 7147874 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6088. Min Act: -0.1700
Data Index: 8699978 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6088. Min Act: -0.1700
Data Index: 6187080 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6088. Min Act: -0.1700
Data Index: 2760134 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.5775. Min Act: -0.1700
Data Index: 7971550 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.6088. Min Act: -0.1700
Data Index: 907203 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.5775. Min Act: -0.1700
Data Index: 3393132 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.5775. Min Act: -0.1700
Data Index: 5072947 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.5775. Min Act: -0.1700
Data Index: 2762010 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8275. Min Range: -4.8275
Max Act: 4.5463. Min Act: -0.1700
Data Index: 5874863 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19