Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1515 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1134. Min Range: -6.1134
Max Act: 6.1134. Min Act: -0.1700
Data Index: 8391155 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.9884. Min Act: -0.1700
Data Index: 8546830 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.7696. Min Act: -0.1700
Data Index: 5134294 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.7384. Min Act: -0.1700
Data Index: 8604246 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3905940 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.7071. Min Act: -0.1700
Data Index: 1532260 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.7071. Min Act: -0.1700
Data Index: 6755108 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.6446. Min Act: -0.1700
Data Index: 119285 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.6446. Min Act: -0.1700
Data Index: 7535389 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.6759. Min Act: -0.1700
Data Index: 1543917 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.6446. Min Act: -0.1700
Data Index: 7868861 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.6134. Min Act: -0.1700
Data Index: 6940579 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.6134. Min Act: -0.1700
Data Index: 750871 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.6134. Min Act: -0.1700
Data Index: 8714972 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.5821. Min Act: -0.1700
Data Index: 4732093 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.5821. Min Act: -0.1700
Data Index: 8216190 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.5509. Min Act: -0.1700
Data Index: 4828949 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.5821. Min Act: -0.1700
Data Index: 8267199 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.5821. Min Act: -0.1700
Data Index: 116089 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1134. Min Range: -6.1134
Max Act: 5.5821. Min Act: -0.1700
Data Index: 50317 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19