Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.9078. Min Act: -0.1700
Data Index: 8681226 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.8765. Min Act: -0.1700
Data Index: 6572196 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.8453. Min Act: -0.1700
Data Index: 5177551 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.7515. Min Act: -0.1700
Data Index: 8711883 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.7515. Min Act: -0.1700
Data Index: 910130 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.7828. Min Act: -0.1700
Data Index: 7803346 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.7203. Min Act: -0.1700
Data Index: 1397777 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6578. Min Act: -0.1700
Data Index: 8681221 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.7203. Min Act: -0.1700
Data Index: 3777574 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6890. Min Act: -0.1700
Data Index: 4304642 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.7203. Min Act: -0.1700
Data Index: 2359151 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6578. Min Act: -0.1700
Data Index: 7049219 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6890. Min Act: -0.1700
Data Index: 7418295 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6578. Min Act: -0.1700
Data Index: 4718418 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6265. Min Act: -0.1700
Data Index: 1395559 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6578. Min Act: -0.1700
Data Index: 7713923 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6265. Min Act: -0.1700
Data Index: 2212314 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6578. Min Act: -0.1700
Data Index: 525702 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6265. Min Act: -0.1700
Data Index: 264554 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9078. Min Range: -6.9078
Max Act: 6.6578. Min Act: -0.1700
Data Index: 1601226 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19