Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1865 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.9979. Min Act: -0.1700
Data Index: 3235848 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.9979. Min Act: -0.1700
Data Index: 5330922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.9979. Min Act: -0.1700
Data Index: 3209241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.9895. Min Act: -0.1700
Data Index: 3353381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.9216. Min Act: -0.1700
Data Index: 2257931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.9046. Min Act: -0.1700
Data Index: 4296017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.9301. Min Act: -0.1700
Data Index: 5640253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8790. Min Act: -0.1700
Data Index: 6552089 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8790. Min Act: -0.1700
Data Index: 2690572 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8704. Min Act: -0.1698
Data Index: 1768683 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8619. Min Act: -0.1700
Data Index: 8438875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8704. Min Act: -0.1700
Data Index: 3289767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8362. Min Act: -0.1700
Data Index: 283678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8362. Min Act: -0.1700
Data Index: 6667030 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8276. Min Act: -0.1700
Data Index: 5495673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8276. Min Act: -0.1700
Data Index: 103353 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8276. Min Act: -0.1700
Data Index: 1602723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8190. Min Act: -0.1700
Data Index: 2788565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8104. Min Act: -0.1700
Data Index: 4644032 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9979. Min Range: -1.9979
Max Act: 1.8190. Min Act: -0.1700
Data Index: 3062910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19