Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1899 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2535. Min Range: -4.2535
Max Act: 4.2535. Min Act: -0.1700
Data Index: 305877 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2535. Min Range: -4.2535
Max Act: 4.1285. Min Act: -0.1700
Data Index: 3269440 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2535. Min Range: -4.2535
Max Act: 4.0660. Min Act: -0.1700
Data Index: 1323716 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2535. Min Range: -4.2535
Max Act: 4.0504. Min Act: -0.1700
Data Index: 779012 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2535. Min Range: -4.2535
Max Act: 4.0035. Min Act: -0.1700
Data Index: 4485408 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9722. Min Act: -0.1700
Data Index: 8442179 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9722. Min Act: -0.1700
Data Index: 4628795 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9566. Min Act: -0.1700
Data Index: 1002179 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9566. Min Act: -0.1700
Data Index: 7975663 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9722. Min Act: -0.1700
Data Index: 7250072 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9253. Min Act: -0.1700
Data Index: 4191598 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.8784. Min Act: -0.1700
Data Index: 1639401 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9253. Min Act: -0.1700
Data Index: 6874207 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9097. Min Act: -0.1700
Data Index: 6762666 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.8784. Min Act: -0.1700
Data Index: 3174753 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.9097. Min Act: -0.1700
Data Index: 5196073 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.8941. Min Act: -0.1700
Data Index: 4015536 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.8784. Min Act: -0.1700
Data Index: 431870 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.8471. Min Act: -0.1700
Data Index: 751989 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2535. Min Range: -4.2535
Max Act: 3.8315. Min Act: -0.1700
Data Index: 8427644 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19