Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.8732. Min Act: -0.1700
Data Index: 4467261 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.8732. Min Act: -0.1700
Data Index: 6833160 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.8732. Min Act: -0.1700
Data Index: 5525657 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.8107. Min Act: -0.1700
Data Index: 8276062 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.7794. Min Act: -0.1700
Data Index: 7136998 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.7794. Min Act: -0.1700
Data Index: 3184024 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.7482. Min Act: -0.1700
Data Index: 1506759 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.7482. Min Act: -0.1700
Data Index: 7562294 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.7169. Min Act: -0.1700
Data Index: 5477124 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6857. Min Act: -0.1700
Data Index: 5439770 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6857. Min Act: -0.1700
Data Index: 3820251 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6857. Min Act: -0.1700
Data Index: 6549390 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6857. Min Act: -0.1700
Data Index: 7926815 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6544. Min Act: -0.1700
Data Index: 7558645 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6857. Min Act: -0.1700
Data Index: 1125907 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6544. Min Act: -0.1700
Data Index: 5633932 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6544. Min Act: -0.1700
Data Index: 7105183 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6232. Min Act: -0.1700
Data Index: 822681 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.6232. Min Act: -0.1700
Data Index: 6310271 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8732. Min Range: -7.8732
Max Act: 7.5919. Min Act: -0.1700
Data Index: 3443912 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19