Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4704 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3816. Min Range: -8.3816
Max Act: 8.3816. Min Act: -0.1700
Data Index: 3064919 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.9441. Min Act: -0.1700
Data Index: 1384131 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.8191. Min Act: -0.1700
Data Index: 5090307 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.6941. Min Act: -0.1700
Data Index: 2972840 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.6941. Min Act: -0.1700
Data Index: 2059958 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.6003. Min Act: -0.1700
Data Index: 4769230 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.5691. Min Act: -0.1700
Data Index: 7234477 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.5378. Min Act: -0.1700
Data Index: 105954 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.4441. Min Act: -0.1700
Data Index: 8344053 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.3816. Min Act: -0.1700
Data Index: 2879788 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.3816. Min Act: -0.1700
Data Index: 284901 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.3191. Min Act: -0.1700
Data Index: 3727230 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.3191. Min Act: -0.1700
Data Index: 7254222 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.2566. Min Act: -0.1700
Data Index: 2524530 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.2878. Min Act: -0.1700
Data Index: 7994615 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.2253. Min Act: -0.1700
Data Index: 4747477 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.1941. Min Act: -0.1700
Data Index: 2868835 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.1941. Min Act: -0.1700
Data Index: 992293 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.1316. Min Act: -0.1700
Data Index: 6757510 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3816. Min Range: -8.3816
Max Act: 7.1628. Min Act: -0.1700
Data Index: 6162848 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19