Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1000 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.7836. Min Act: -0.1698
Data Index: 5477827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.7664. Min Act: -0.1700
Data Index: 5731750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.7145. Min Act: -0.1700
Data Index: 5961066 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.7232. Min Act: -0.1698
Data Index: 811597 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.7145. Min Act: -0.1700
Data Index: 7076228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.7059. Min Act: -0.1700
Data Index: 48832 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.7059. Min Act: -0.1700
Data Index: 3577469 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6885. Min Act: -0.1698
Data Index: 318584 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6972. Min Act: -0.1700
Data Index: 1503804 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6798. Min Act: -0.1700
Data Index: 7802779 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6712. Min Act: -0.1700
Data Index: 7858247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6885. Min Act: -0.1700
Data Index: 7041134 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6451. Min Act: -0.1699
Data Index: 2059406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6451. Min Act: -0.1700
Data Index: 5046866 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6364. Min Act: -0.1700
Data Index: 5943339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6276. Min Act: -0.1700
Data Index: 5108412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6364. Min Act: -0.1700
Data Index: 7811307 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6276. Min Act: -0.1700
Data Index: 4559292 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6364. Min Act: -0.1700
Data Index: 1034845 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7836. Min Range: -1.7836
Max Act: 1.6276. Min Act: -0.1700
Data Index: 3322483 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19