Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.6024. Min Act: -0.1700
Data Index: 7921497 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.6024. Min Act: -0.1700
Data Index: 12604 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.5087. Min Act: -0.1700
Data Index: 6216802 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.4462. Min Act: -0.1700
Data Index: 3179357 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.3837. Min Act: -0.1700
Data Index: 3991070 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.3524. Min Act: -0.1700
Data Index: 111420 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.3524. Min Act: -0.1700
Data Index: 4625646 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.2899. Min Act: -0.1700
Data Index: 1687686 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.2899. Min Act: -0.1700
Data Index: 4625645 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.2587. Min Act: -0.1700
Data Index: 706132 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.2587. Min Act: -0.1700
Data Index: 3991069 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.2274. Min Act: -0.1700
Data Index: 1517901 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.2274. Min Act: -0.1700
Data Index: 3439427 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.1962. Min Act: -0.1700
Data Index: 6456478 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3139688 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.1962. Min Act: -0.1700
Data Index: 4841339 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.2274. Min Act: -0.1700
Data Index: 4429153 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.1962. Min Act: -0.1700
Data Index: 1795326 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.1962. Min Act: -0.1700
Data Index: 243731 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6024. Min Range: -5.6024
Max Act: 5.1649. Min Act: -0.1700
Data Index: 3522674 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19