Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0342. Min Range: -5.0342
Max Act: 5.0342. Min Act: -0.1700
Data Index: 4756218 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0342. Min Range: -5.0342
Max Act: 5.0029. Min Act: -0.1700
Data Index: 6652339 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8779. Min Act: -0.1700
Data Index: 3087936 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8154. Min Act: -0.1700
Data Index: 1601099 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8467. Min Act: -0.1700
Data Index: 3149004 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8467. Min Act: -0.1700
Data Index: 1952378 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8467. Min Act: -0.1700
Data Index: 4432442 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8154. Min Act: -0.1700
Data Index: 7993861 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8154. Min Act: -0.1700
Data Index: 4508059 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8154. Min Act: -0.1700
Data Index: 1090023 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7842. Min Act: -0.1700
Data Index: 559322 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7529. Min Act: -0.1700
Data Index: 1633646 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7529. Min Act: -0.1700
Data Index: 5966901 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 6332171 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 5592941 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.6904. Min Act: -0.1700
Data Index: 3989895 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 5316814 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 2603376 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 1240700 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 328728 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19