Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.9322. Min Act: -0.1700
Data Index: 2809699 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.9322. Min Act: -0.1700
Data Index: 3405118 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.9005. Min Act: -0.1700
Data Index: 4239528 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8688. Min Act: -0.1700
Data Index: 1201285 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8688. Min Act: -0.1700
Data Index: 2785489 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8211. Min Act: -0.1700
Data Index: 8367272 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8370. Min Act: -0.1700
Data Index: 2652848 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8052. Min Act: -0.1700
Data Index: 4150005 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8211. Min Act: -0.1700
Data Index: 8400071 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8052. Min Act: -0.1700
Data Index: 8159391 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8370. Min Act: -0.1700
Data Index: 908302 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8370. Min Act: -0.1700
Data Index: 953155 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8211. Min Act: -0.1700
Data Index: 3943119 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8211. Min Act: -0.1700
Data Index: 3688615 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8052. Min Act: -0.1700
Data Index: 1805991 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8052. Min Act: -0.1700
Data Index: 908299 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.7893. Min Act: -0.1700
Data Index: 2419373 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8052. Min Act: -0.1700
Data Index: 6543259 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8211. Min Act: -0.1700
Data Index: 4689734 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9322. Min Range: -2.9322
Max Act: 2.8052. Min Act: -0.1700
Data Index: 908300 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19