Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.4430. Min Act: -0.1700
Data Index: 3415320 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.2867. Min Act: -0.1700
Data Index: 6582272 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.1930. Min Act: -0.1700
Data Index: 2506025 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.0992. Min Act: -0.1700
Data Index: 818879 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.0367. Min Act: -0.1700
Data Index: 4225298 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.0055. Min Act: -0.1700
Data Index: 7129139 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.0055. Min Act: -0.1700
Data Index: 8824753 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.9742. Min Act: -0.1700
Data Index: 8635488 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.9742. Min Act: -0.1700
Data Index: 7245236 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4430. Min Range: -5.4430
Max Act: 5.0055. Min Act: -0.1700
Data Index: 7646355 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.9117. Min Act: -0.1700
Data Index: 4463082 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.9117. Min Act: -0.1700
Data Index: 686906 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.9117. Min Act: -0.1700
Data Index: 1700140 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.8805. Min Act: -0.1700
Data Index: 5157641 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.8805. Min Act: -0.1700
Data Index: 2036954 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.8805. Min Act: -0.1700
Data Index: 1313868 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.8805. Min Act: -0.1700
Data Index: 8117747 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.8492. Min Act: -0.1700
Data Index: 225251 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.8492. Min Act: -0.1700
Data Index: 7656848 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4430. Min Range: -5.4430
Max Act: 4.8492. Min Act: -0.1700
Data Index: 3636693 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19