Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.9044. Min Act: -0.1700
Data Index: 3215208 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.8419. Min Act: -0.1700
Data Index: 8663792 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.6857. Min Act: -0.1700
Data Index: 8543037 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.6232. Min Act: -0.1700
Data Index: 2346748 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.5919. Min Act: -0.1700
Data Index: 7970989 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.5607. Min Act: -0.1700
Data Index: 5069194 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.5607. Min Act: -0.1700
Data Index: 3776454 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.4669. Min Act: -0.1700
Data Index: 8663790 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.4357. Min Act: -0.1700
Data Index: 1296883 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.4669. Min Act: -0.1700
Data Index: 8895 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.4669. Min Act: -0.1700
Data Index: 7543245 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.4044. Min Act: -0.1700
Data Index: 2718610 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.4044. Min Act: -0.1700
Data Index: 8467972 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.4044. Min Act: -0.1700
Data Index: 468903 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.3732. Min Act: -0.1700
Data Index: 1075533 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.3732. Min Act: -0.1700
Data Index: 2328940 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.3107. Min Act: -0.1700
Data Index: 4343784 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.3419. Min Act: -0.1700
Data Index: 47365 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.2794. Min Act: -0.1700
Data Index: 230298 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9044. Min Range: -6.9044
Max Act: 6.2794. Min Act: -0.1700
Data Index: 3880420 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19