Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2094 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.4844. Min Act: -0.1700
Data Index: 5208073 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.4844. Min Act: -0.1700
Data Index: 575300 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.2969. Min Act: -0.1700
Data Index: 6159637 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.2344. Min Act: -0.1700
Data Index: 2813026 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.1094. Min Act: -0.1700
Data Index: 627199 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.1094. Min Act: -0.1700
Data Index: 7993429 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.1719. Min Act: -0.1700
Data Index: 1827250 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.1094. Min Act: -0.1700
Data Index: 575287 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.0469. Min Act: -0.1700
Data Index: 5465843 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.0469. Min Act: -0.1700
Data Index: 5563509 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4844. Min Range: -9.4844
Max Act: 9.0469. Min Act: -0.1700
Data Index: 4786985 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9219. Min Act: -0.1700
Data Index: 6774928 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9844. Min Act: -0.1700
Data Index: 320968 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9219. Min Act: -0.1700
Data Index: 3035783 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9219. Min Act: -0.1700
Data Index: 1492513 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9219. Min Act: -0.1700
Data Index: 8440697 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9219. Min Act: -0.1700
Data Index: 2054868 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.8594. Min Act: -0.1700
Data Index: 6159641 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9219. Min Act: -0.1700
Data Index: 2177520 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4844. Min Range: -9.4844
Max Act: 8.9219. Min Act: -0.1700
Data Index: 5330954 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19