Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2080 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.9809. Min Act: -0.1700
Data Index: 3104763 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.8871. Min Act: -0.1700
Data Index: 1421095 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.8871. Min Act: -0.1700
Data Index: 844612 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.8245. Min Act: -0.1700
Data Index: 1604926 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.7933. Min Act: -0.1700
Data Index: 8127046 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.7307. Min Act: -0.1700
Data Index: 3858937 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.7620. Min Act: -0.1700
Data Index: 2827756 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.7307. Min Act: -0.1700
Data Index: 1690020 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6994. Min Act: -0.1700
Data Index: 3254406 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6994. Min Act: -0.1700
Data Index: 956290 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6994. Min Act: -0.1700
Data Index: 3934306 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6994. Min Act: -0.1700
Data Index: 552126 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.7307. Min Act: -0.1700
Data Index: 1978797 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.7307. Min Act: -0.1700
Data Index: 1209518 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6994. Min Act: -0.1700
Data Index: 5039599 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.7307. Min Act: -0.1700
Data Index: 2955002 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6838. Min Act: -0.1700
Data Index: 6323183 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6681. Min Act: -0.1700
Data Index: 7544884 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6525. Min Act: -0.1700
Data Index: 2550475 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9809. Min Range: -3.9809
Max Act: 3.6838. Min Act: -0.1700
Data Index: 888846 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19