Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4566 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.3860. Min Act: -0.0001
Data Index: 1309962 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.4057. Min Act: -0.0001
Data Index: 385757 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.2855. Min Act: -0.0001
Data Index: 1126887 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.1627. Min Act: -0.0001
Data Index: 746412 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.0857. Min Act: -0.0001
Data Index: 114584 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.1287. Min Act: -0.0001
Data Index: 967236 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.0360. Min Act: -0.0001
Data Index: 1109519 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.2531. Min Act: -0.0001
Data Index: 158230 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.1214. Min Act: -0.0001
Data Index: 357060 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4057. Min Range: -1.4057
Max Act: 0.8708. Min Act: -0.0001
Data Index: 1352871 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.1966. Min Act: -0.0001
Data Index: 788864 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.0630. Min Act: -0.0001
Data Index: 1288889 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.0644. Min Act: -0.0001
Data Index: 1117729 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.1330. Min Act: -0.0001
Data Index: 132724 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.1495. Min Act: -0.0001
Data Index: 6352 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.0243. Min Act: -0.0001
Data Index: 739059 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.0672. Min Act: -0.0001
Data Index: 147048 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.2100. Min Act: -0.0001
Data Index: 266983 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4057. Min Range: -1.4057
Max Act: 1.1717. Min Act: -0.0001
Data Index: 1190116 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4057. Min Range: -1.4057
Max Act: 0.7652. Min Act: -0.0001
Data Index: 581635 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19