Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1084 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1172. Min Range: -6.1172
Max Act: 6.1172. Min Act: -0.1700
Data Index: 3936384 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.8672. Min Act: -0.1700
Data Index: 721531 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.8984. Min Act: -0.1700
Data Index: 1665966 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.8047. Min Act: -0.1700
Data Index: 4860317 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.8359. Min Act: -0.1700
Data Index: 1229417 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.8359. Min Act: -0.1700
Data Index: 3249249 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.8359. Min Act: -0.1700
Data Index: 7950645 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.7734. Min Act: -0.1700
Data Index: 6214450 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.7422. Min Act: -0.1700
Data Index: 7104415 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.7109. Min Act: -0.1700
Data Index: 467159 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.7109. Min Act: -0.1700
Data Index: 613914 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.6797. Min Act: -0.1700
Data Index: 2240201 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.7109. Min Act: -0.1700
Data Index: 5427213 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.6172. Min Act: -0.1700
Data Index: 7580268 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.6484. Min Act: -0.1700
Data Index: 4842967 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.6172. Min Act: -0.1700
Data Index: 6459516 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.6484. Min Act: -0.1700
Data Index: 5751199 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.5859. Min Act: -0.1700
Data Index: 4846903 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.5859. Min Act: -0.1700
Data Index: 46521 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1172. Min Range: -6.1172
Max Act: 5.5859. Min Act: -0.1700
Data Index: 6488863 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19