Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1762 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.7312. Min Act: -0.1700
Data Index: 3786201 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.7000. Min Act: -0.1700
Data Index: 2900496 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.6375. Min Act: -0.1700
Data Index: 8142743 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.5437. Min Act: -0.1700
Data Index: 2138891 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.5437. Min Act: -0.1700
Data Index: 6004491 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.5125. Min Act: -0.1700
Data Index: 6561760 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4812. Min Act: -0.1700
Data Index: 1061730 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4812. Min Act: -0.1700
Data Index: 2099018 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4187. Min Act: -0.1700
Data Index: 4857241 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.4500. Min Act: -0.1700
Data Index: 5938520 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3875. Min Act: -0.1700
Data Index: 477552 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3875. Min Act: -0.1700
Data Index: 2691313 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3562. Min Act: -0.1700
Data Index: 6866123 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3250. Min Act: -0.1700
Data Index: 8648801 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3250. Min Act: -0.1700
Data Index: 1257645 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3250. Min Act: -0.1700
Data Index: 2665287 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3250. Min Act: -0.1700
Data Index: 4307090 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3562. Min Act: -0.1700
Data Index: 6051686 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.3250. Min Act: -0.1700
Data Index: 6310416 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7312. Min Range: -4.7312
Max Act: 4.2937. Min Act: -0.1700
Data Index: 5021230 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19