Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.1066. Min Act: -0.1700
Data Index: 3032156 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.1066. Min Act: -0.1698
Data Index: 8656481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0563. Min Act: -0.1700
Data Index: 5458461 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0395. Min Act: -0.1700
Data Index: 3832573 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0226. Min Act: -0.1700
Data Index: 8375210 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0226. Min Act: -0.1698
Data Index: 1384911 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0058. Min Act: -0.1700
Data Index: 7971344 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0226. Min Act: -0.1700
Data Index: 7719729 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0058. Min Act: -0.1700
Data Index: 7129207 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0226. Min Act: -0.1700
Data Index: 6619280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1066. Min Range: -2.1066
Max Act: 1.9889. Min Act: -0.1700
Data Index: 4306270 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0058. Min Act: -0.1698
Data Index: 5842267 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1066. Min Range: -2.1066
Max Act: 1.9889. Min Act: -0.1700
Data Index: 1652217 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0058. Min Act: -0.1700
Data Index: 7239730 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1066. Min Range: -2.1066
Max Act: 1.9889. Min Act: -0.1700
Data Index: 5146786 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1066. Min Range: -2.1066
Max Act: 1.9889. Min Act: -0.1694
Data Index: 8327932 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1066. Min Range: -2.1066
Max Act: 1.9889. Min Act: -0.1700
Data Index: 7026079 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1066. Min Range: -2.1066
Max Act: 1.9889. Min Act: -0.1700
Data Index: 3381232 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1066. Min Range: -2.1066
Max Act: 2.0058. Min Act: -0.1700
Data Index: 7921296 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1066. Min Range: -2.1066
Max Act: 1.9889. Min Act: -0.1700
Data Index: 7731320 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19