Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.4744. Min Act: -0.1700
Data Index: 5307149 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.3806. Min Act: -0.1700
Data Index: 8250360 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.2869. Min Act: -0.1700
Data Index: 1202978 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.2869. Min Act: -0.1700
Data Index: 1997312 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.2556. Min Act: -0.1700
Data Index: 1660737 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.2244. Min Act: -0.1700
Data Index: 3858100 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1931. Min Act: -0.1700
Data Index: 7992126 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1931. Min Act: -0.1700
Data Index: 7235524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1931. Min Act: -0.1700
Data Index: 990485 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1619. Min Act: -0.1700
Data Index: 4386059 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1619. Min Act: -0.1700
Data Index: 5885430 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1619. Min Act: -0.1700
Data Index: 2439682 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1931. Min Act: -0.1700
Data Index: 8162276 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1931. Min Act: -0.1700
Data Index: 7161009 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1619. Min Act: -0.1700
Data Index: 3944889 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1306. Min Act: -0.1700
Data Index: 5548873 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1306. Min Act: -0.1700
Data Index: 254270 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1306. Min Act: -0.1700
Data Index: 6066868 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1306. Min Act: -0.1700
Data Index: 6181257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4744. Min Range: -5.4744
Max Act: 5.1619. Min Act: -0.1700
Data Index: 3306988 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19