Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2894 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.3148. Min Range: -3.3148
Max Act: 3.3148. Min Act: -0.0001
Data Index: 249965 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.9302. Min Act: -0.0001
Data Index: 900135 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.7688. Min Act: -0.0001
Data Index: 903729 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.6758. Min Act: -0.0001
Data Index: 331780 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.4933. Min Act: -0.0001
Data Index: 145404 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.6232. Min Act: -0.0001
Data Index: 1308357 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.4892. Min Act: -0.0001
Data Index: 761268 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.1488. Min Act: -0.0001
Data Index: 1333867 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.4688. Min Act: -0.0001
Data Index: 1057413 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.3508. Min Act: -0.0001
Data Index: 863417 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.4710. Min Act: -0.0001
Data Index: 340788 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.0206. Min Act: -0.0001
Data Index: 325855 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.4446. Min Act: -0.0001
Data Index: 477092 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.2594. Min Act: -0.0001
Data Index: 283853 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.3791. Min Act: -0.0001
Data Index: 325278 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.2402. Min Act: -0.0001
Data Index: 964973 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.3600. Min Act: -0.0001
Data Index: 790425 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.3741. Min Act: -0.0001
Data Index: 242015 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.3465. Min Act: -0.0001
Data Index: 16977 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3148. Min Range: -3.3148
Max Act: 2.2169. Min Act: -0.0001
Data Index: 774071 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19