Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0744. Min Range: -3.0744
Max Act: 3.0744. Min Act: -0.1700
Data Index: 3753215 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9797. Min Act: -0.1700
Data Index: 5917924 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9639. Min Act: -0.1700
Data Index: 8160506 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9163. Min Act: -0.1700
Data Index: 1029263 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9163. Min Act: -0.1700
Data Index: 2839882 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9163. Min Act: -0.1700
Data Index: 3839785 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9322. Min Act: -0.1700
Data Index: 5385926 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9322. Min Act: -0.1700
Data Index: 8351304 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.9005. Min Act: -0.1700
Data Index: 8201373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8846. Min Act: -0.1700
Data Index: 4756725 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2944117 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8688. Min Act: -0.1700
Data Index: 5278477 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8846. Min Act: -0.1700
Data Index: 5730275 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8846. Min Act: -0.1700
Data Index: 3485343 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8688. Min Act: -0.1700
Data Index: 7665440 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8846. Min Act: -0.1700
Data Index: 7058795 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8211. Min Act: -0.1700
Data Index: 4445112 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2886562 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8370. Min Act: -0.1700
Data Index: 590402 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0744. Min Range: -3.0744
Max Act: 2.8370. Min Act: -0.1700
Data Index: 6278973 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19