Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2135 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2454. Min Range: -6.2454
Max Act: 6.2454. Min Act: -0.1700
Data Index: 1787573 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.9954. Min Act: -0.1700
Data Index: 8348125 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.9329. Min Act: -0.1700
Data Index: 4158139 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.8704. Min Act: -0.1700
Data Index: 5493724 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.7142. Min Act: -0.1700
Data Index: 8369211 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.7454. Min Act: -0.1700
Data Index: 3492368 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 8039561 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 6298294 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.7142. Min Act: -0.1700
Data Index: 199755 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 2490960 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6517. Min Act: -0.1700
Data Index: 3204046 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6517. Min Act: -0.1700
Data Index: 2880372 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6517. Min Act: -0.1700
Data Index: 5437893 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 4741205 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6517. Min Act: -0.1700
Data Index: 7724254 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6829. Min Act: -0.1700
Data Index: 7388981 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.6204. Min Act: -0.1700
Data Index: 498874 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5892. Min Act: -0.1700
Data Index: 5857883 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5579. Min Act: -0.1700
Data Index: 2121709 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2454. Min Range: -6.2454
Max Act: 5.5579. Min Act: -0.1700
Data Index: 7312267 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19