Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 39 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.5935. Min Act: -0.1700
Data Index: 4045356 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.5623. Min Act: -0.1700
Data Index: 5328842 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.4685. Min Act: -0.1700
Data Index: 4794892 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.4373. Min Act: -0.1700
Data Index: 1571356 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.4373. Min Act: -0.1700
Data Index: 8023661 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.4060. Min Act: -0.1700
Data Index: 6742006 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3748. Min Act: -0.1700
Data Index: 2553324 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3748. Min Act: -0.1700
Data Index: 6356961 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3435. Min Act: -0.1700
Data Index: 1370534 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3435. Min Act: -0.1700
Data Index: 3193565 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3435. Min Act: -0.1700
Data Index: 6728107 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3123. Min Act: -0.1700
Data Index: 1208256 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3123. Min Act: -0.1700
Data Index: 1191366 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.3435. Min Act: -0.1700
Data Index: 5300567 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.2498. Min Act: -0.1700
Data Index: 1015446 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.2185. Min Act: -0.1700
Data Index: 354887 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.1873. Min Act: -0.1700
Data Index: 3994703 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.2185. Min Act: -0.1700
Data Index: 5252266 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.1873. Min Act: -0.1700
Data Index: 1337969 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5935. Min Range: -7.5935
Max Act: 7.1873. Min Act: -0.1700
Data Index: 4969878 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19