Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.4921. Min Act: -0.1700
Data Index: 240617 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.4608. Min Act: -0.1700
Data Index: 64131 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.4295. Min Act: -0.1700
Data Index: 2694905 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3983. Min Act: -0.1700
Data Index: 5832726 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3670. Min Act: -0.1700
Data Index: 5493740 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3670. Min Act: -0.1700
Data Index: 4016464 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3670. Min Act: -0.1700
Data Index: 8796133 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2733. Min Act: -0.1700
Data Index: 4882535 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3670. Min Act: -0.1700
Data Index: 2024096 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3045. Min Act: -0.1700
Data Index: 5145796 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3358. Min Act: -0.1700
Data Index: 984301 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2733. Min Act: -0.1700
Data Index: 7646846 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3045. Min Act: -0.1700
Data Index: 926017 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3045. Min Act: -0.1700
Data Index: 2783082 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2733. Min Act: -0.1700
Data Index: 1287494 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2420. Min Act: -0.1700
Data Index: 5151190 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3358. Min Act: -0.1700
Data Index: 1606916 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2420. Min Act: -0.1700
Data Index: 2275889 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2420. Min Act: -0.1700
Data Index: 2577048 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2420. Min Act: -0.1700
Data Index: 7026610 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19