Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2985. Min Act: -0.1700
Data Index: 1164488 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2673. Min Act: -0.1700
Data Index: 4456409 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2985. Min Act: -0.1700
Data Index: 4788949 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2360. Min Act: -0.1700
Data Index: 612302 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2673. Min Act: -0.1700
Data Index: 6726519 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2047. Min Act: -0.1700
Data Index: 2385738 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2360. Min Act: -0.1700
Data Index: 3709502 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2047. Min Act: -0.1700
Data Index: 1224714 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1735. Min Act: -0.1700
Data Index: 1284568 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1735. Min Act: -0.1700
Data Index: 898337 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1422. Min Act: -0.1700
Data Index: 266466 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2047. Min Act: -0.1700
Data Index: 2750530 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2047. Min Act: -0.1700
Data Index: 2951179 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1735. Min Act: -0.1700
Data Index: 6807699 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1422. Min Act: -0.1700
Data Index: 6989741 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.2047. Min Act: -0.1700
Data Index: 8637403 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1735. Min Act: -0.1700
Data Index: 8638216 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1735. Min Act: -0.1700
Data Index: 1144625 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1735. Min Act: -0.1700
Data Index: 4787023 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2985. Min Range: -4.2985
Max Act: 4.1422. Min Act: -0.1700
Data Index: 3977512 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19