Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1491 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.3504. Min Act: -0.1700
Data Index: 3395593 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.3504. Min Act: -0.1700
Data Index: 6071633 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.3190. Min Act: -0.1700
Data Index: 2081843 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.3190. Min Act: -0.1700
Data Index: 8318737 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.3190. Min Act: -0.1700
Data Index: 4113317 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.3190. Min Act: -0.1700
Data Index: 7049098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.3190. Min Act: -0.1700
Data Index: 6412256 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 2586171 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 8363429 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 7175491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 6361149 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2562. Min Act: -0.1700
Data Index: 7198 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 5213490 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 4978757 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 4276465 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 962150 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 3706710 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2876. Min Act: -0.1700
Data Index: 3369648 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2562. Min Act: -0.1700
Data Index: 1712482 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3504. Min Range: -3.3504
Max Act: 3.2562. Min Act: -0.1700
Data Index: 1762242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19