Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.9045. Min Act: -0.1700
Data Index: 4025525 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.9045. Min Act: -0.1700
Data Index: 3412799 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.8107. Min Act: -0.1700
Data Index: 8149299 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.7482. Min Act: -0.1700
Data Index: 3918958 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.7170. Min Act: -0.1700
Data Index: 1671974 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.6857. Min Act: -0.1700
Data Index: 607954 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.6545. Min Act: -0.1700
Data Index: 5242651 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.6232. Min Act: -0.1700
Data Index: 6144159 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.6232. Min Act: -0.1700
Data Index: 4753867 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.5920. Min Act: -0.1700
Data Index: 5267721 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.6232. Min Act: -0.1700
Data Index: 7274310 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.5920. Min Act: -0.1700
Data Index: 5109418 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.6232. Min Act: -0.1700
Data Index: 7685572 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.5920. Min Act: -0.1700
Data Index: 7367443 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.6232. Min Act: -0.1700
Data Index: 6044463 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.5920. Min Act: -0.1700
Data Index: 5355019 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.5295. Min Act: -0.1700
Data Index: 2308308 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.5607. Min Act: -0.1700
Data Index: 2869808 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.5295. Min Act: -0.1700
Data Index: 4724103 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9045. Min Range: -5.9045
Max Act: 5.4982. Min Act: -0.1700
Data Index: 3839789 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19