Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1760 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1326. Min Range: -9.1326
Max Act: 9.1326. Min Act: -0.1700
Data Index: 4709058 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1326. Min Range: -9.1326
Max Act: 8.2576. Min Act: -0.1700
Data Index: 5649061 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1326. Min Range: -9.1326
Max Act: 8.1638. Min Act: -0.1700
Data Index: 466102 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1326. Min Range: -9.1326
Max Act: 8.0076. Min Act: -0.1700
Data Index: 6578054 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.9138. Min Act: -0.1700
Data Index: 5709929 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.9763. Min Act: -0.1700
Data Index: 6100264 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.9451. Min Act: -0.1700
Data Index: 498395 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.8826. Min Act: -0.1700
Data Index: 5076078 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.8513. Min Act: -0.1700
Data Index: 4491808 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.7888. Min Act: -0.1700
Data Index: 5098448 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.7888. Min Act: -0.1700
Data Index: 5829712 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.7263. Min Act: -0.1700
Data Index: 907848 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.7576. Min Act: -0.1700
Data Index: 4465752 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.7263. Min Act: -0.1700
Data Index: 2675878 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.6951. Min Act: -0.1700
Data Index: 1763089 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.7263. Min Act: -0.1700
Data Index: 4029338 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.6951. Min Act: -0.1700
Data Index: 6943517 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.6951. Min Act: -0.1700
Data Index: 3170038 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.6638. Min Act: -0.1700
Data Index: 7056713 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1326. Min Range: -9.1326
Max Act: 7.6638. Min Act: -0.1700
Data Index: 4127083 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19