Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2194 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.6190. Min Act: -0.1700
Data Index: 3929781 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.5877. Min Act: -0.1700
Data Index: 4019703 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.4938. Min Act: -0.1700
Data Index: 4413806 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.5094. Min Act: -0.1700
Data Index: 1514058 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.4938. Min Act: -0.1700
Data Index: 132361 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.5094. Min Act: -0.1700
Data Index: 6127701 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.4624. Min Act: -0.1700
Data Index: 8546759 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.4624. Min Act: -0.1700
Data Index: 5171898 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.4311. Min Act: -0.1700
Data Index: 6800094 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.4468. Min Act: -0.1700
Data Index: 6161838 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3997. Min Act: -0.1700
Data Index: 2447905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3997. Min Act: -0.1700
Data Index: 4517185 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3370. Min Act: -0.1700
Data Index: 4249631 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.4154. Min Act: -0.1700
Data Index: 7411683 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3997. Min Act: -0.1700
Data Index: 5084341 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3841. Min Act: -0.1700
Data Index: 5079358 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3997. Min Act: -0.1700
Data Index: 410047 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3997. Min Act: -0.1700
Data Index: 5171896 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3684. Min Act: -0.1700
Data Index: 1448000 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6190. Min Range: -3.6190
Max Act: 3.3527. Min Act: -0.1700
Data Index: 4989697 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19