Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1155. Min Range: -6.1155
Max Act: 6.1155. Min Act: -0.1700
Data Index: 2590678 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.9905. Min Act: -0.1700
Data Index: 7136187 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.9905. Min Act: -0.1700
Data Index: 8052918 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.9280. Min Act: -0.1700
Data Index: 6907426 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.8655. Min Act: -0.1700
Data Index: 5790449 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.8655. Min Act: -0.1700
Data Index: 7863072 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.8342. Min Act: -0.1700
Data Index: 17570 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.8030. Min Act: -0.1700
Data Index: 5704937 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.8030. Min Act: -0.1700
Data Index: 5985401 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.7717. Min Act: -0.1700
Data Index: 17571 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.7405. Min Act: -0.1700
Data Index: 787829 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.7405. Min Act: -0.1700
Data Index: 68632 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.7092. Min Act: -0.1700
Data Index: 1603598 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.7092. Min Act: -0.1700
Data Index: 2138806 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.7092. Min Act: -0.1700
Data Index: 124071 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.6780. Min Act: -0.1700
Data Index: 8014231 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.6780. Min Act: -0.1700
Data Index: 17569 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.6780. Min Act: -0.1700
Data Index: 1886049 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.7092. Min Act: -0.1700
Data Index: 531563 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1155. Min Range: -6.1155
Max Act: 5.6780. Min Act: -0.1700
Data Index: 3208706 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19