Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.7124. Min Act: -0.1700
Data Index: 2736622 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.7124. Min Act: -0.1700
Data Index: 713894 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.6812. Min Act: -0.1700
Data Index: 1135306 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.6812. Min Act: -0.1700
Data Index: 2467658 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.6812. Min Act: -0.1700
Data Index: 3496559 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.6499. Min Act: -0.1700
Data Index: 6544239 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.5874. Min Act: -0.1700
Data Index: 1208669 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.5874. Min Act: -0.1700
Data Index: 6771430 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.5874. Min Act: -0.1700
Data Index: 818990 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.6187. Min Act: -0.1700
Data Index: 7788032 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.5562. Min Act: -0.1700
Data Index: 4108625 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.4937. Min Act: -0.1700
Data Index: 2697442 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.5562. Min Act: -0.1700
Data Index: 8060151 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.5249. Min Act: -0.1700
Data Index: 220902 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.5249. Min Act: -0.1700
Data Index: 2061766 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.4937. Min Act: -0.1700
Data Index: 7880020 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.4624. Min Act: -0.1700
Data Index: 4765069 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.4312. Min Act: -0.1700
Data Index: 6944281 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.3999. Min Act: -0.1700
Data Index: 978848 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7124. Min Range: -4.7124
Max Act: 4.4624. Min Act: -0.1700
Data Index: 347617 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19