Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.2789. Min Act: -0.1700
Data Index: 8832064 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.1852. Min Act: -0.1700
Data Index: 4258111 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.1539. Min Act: -0.1700
Data Index: 390204 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.1539. Min Act: -0.1700
Data Index: 7348919 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.1539. Min Act: -0.1700
Data Index: 4643268 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.1227. Min Act: -0.1700
Data Index: 910276 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0914. Min Act: -0.1700
Data Index: 8770777 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.1227. Min Act: -0.1700
Data Index: 2057738 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0914. Min Act: -0.1700
Data Index: 7976691 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0914. Min Act: -0.1700
Data Index: 2458870 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0601. Min Act: -0.1700
Data Index: 1688745 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0601. Min Act: -0.1700
Data Index: 2551014 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0601. Min Act: -0.1700
Data Index: 6742995 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2789. Min Range: -4.2789
Max Act: 3.9976. Min Act: -0.1700
Data Index: 258688 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0289. Min Act: -0.1700
Data Index: 4590678 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0289. Min Act: -0.1700
Data Index: 3366345 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2789. Min Range: -4.2789
Max Act: 4.0289. Min Act: -0.1700
Data Index: 5337596 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2789. Min Range: -4.2789
Max Act: 3.9976. Min Act: -0.1700
Data Index: 1288967 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2789. Min Range: -4.2789
Max Act: 3.9976. Min Act: -0.1700
Data Index: 7174528 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2789. Min Range: -4.2789
Max Act: 3.9976. Min Act: -0.1700
Data Index: 3802655 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19