Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1055 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.8801. Min Act: -0.1700
Data Index: 2654244 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.5988. Min Act: -0.1700
Data Index: 7626579 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.6613. Min Act: -0.1700
Data Index: 7033295 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.6926. Min Act: -0.1700
Data Index: 5796275 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.5676. Min Act: -0.1700
Data Index: 6005702 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.5988. Min Act: -0.1700
Data Index: 6252200 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.4426. Min Act: -0.1700
Data Index: 8178447 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.3488. Min Act: -0.1700
Data Index: 8612262 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.3801. Min Act: -0.1700
Data Index: 262972 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.3176. Min Act: -0.1700
Data Index: 4586210 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.3176. Min Act: -0.1700
Data Index: 3936591 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.2863. Min Act: -0.1700
Data Index: 8396065 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.2238. Min Act: -0.1700
Data Index: 968809 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.2551. Min Act: -0.1700
Data Index: 4441477 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1926. Min Act: -0.1700
Data Index: 2028066 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.2238. Min Act: -0.1700
Data Index: 3310356 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1613. Min Act: -0.1700
Data Index: 3690560 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1301. Min Act: -0.1700
Data Index: 4962493 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1926. Min Act: -0.1700
Data Index: 3808896 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8801. Min Range: -6.8801
Max Act: 6.1613. Min Act: -0.1700
Data Index: 7077135 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19