Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.8427. Min Act: -0.1700
Data Index: 6137055 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.5927. Min Act: -0.1700
Data Index: 1927664 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.5927. Min Act: -0.1700
Data Index: 2069499 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.5615. Min Act: -0.1700
Data Index: 2997624 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.4990. Min Act: -0.1700
Data Index: 2011840 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.4990. Min Act: -0.1700
Data Index: 2124192 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.4990. Min Act: -0.1700
Data Index: 7535833 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.4052. Min Act: -0.1700
Data Index: 5261933 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.4052. Min Act: -0.1700
Data Index: 2457331 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.3427. Min Act: -0.1700
Data Index: 1916065 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.3115. Min Act: -0.1700
Data Index: 819404 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.3115. Min Act: -0.1700
Data Index: 7627647 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.2802. Min Act: -0.1700
Data Index: 8772040 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.2802. Min Act: -0.1700
Data Index: 904672 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.2490. Min Act: -0.1700
Data Index: 7038931 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.2490. Min Act: -0.1700
Data Index: 3505716 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.2490. Min Act: -0.1700
Data Index: 978777 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.2177. Min Act: -0.1700
Data Index: 2225636 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.1865. Min Act: -0.1700
Data Index: 7169027 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8427. Min Range: -5.8427
Max Act: 5.2177. Min Act: -0.1700
Data Index: 6501046 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19