Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5064 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2977. Min Range: -7.2977
Max Act: 7.2977. Min Act: -0.1700
Data Index: 690442 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2977. Min Range: -7.2977
Max Act: 7.2352. Min Act: -0.1700
Data Index: 5400494 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2977. Min Range: -7.2977
Max Act: 7.1102. Min Act: -0.1700
Data Index: 3730680 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2977. Min Range: -7.2977
Max Act: 7.1102. Min Act: -0.1700
Data Index: 959995 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2977. Min Range: -7.2977
Max Act: 7.0165. Min Act: -0.1700
Data Index: 1287871 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.9852. Min Act: -0.1700
Data Index: 3861911 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.9227. Min Act: -0.1700
Data Index: 7952751 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.8915. Min Act: -0.1700
Data Index: 5680584 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.8915. Min Act: -0.1700
Data Index: 1696924 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.8915. Min Act: -0.1700
Data Index: 3292931 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.8602. Min Act: -0.1700
Data Index: 3757696 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.8602. Min Act: -0.1700
Data Index: 4201483 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.7977. Min Act: -0.1700
Data Index: 3763380 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.8290. Min Act: -0.1700
Data Index: 898658 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.7977. Min Act: -0.1700
Data Index: 971134 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.7352. Min Act: -0.1700
Data Index: 2599517 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.7665. Min Act: -0.1700
Data Index: 4487712 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.7665. Min Act: -0.1700
Data Index: 8408487 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.7352. Min Act: -0.1700
Data Index: 7442755 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2977. Min Range: -7.2977
Max Act: 6.7665. Min Act: -0.1700
Data Index: 468236 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19