Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5983 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.2685. Min Act: -0.0001
Data Index: 1367386 (Python Code)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0937. Min Act: -0.0001
Data Index: 373935 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.1582. Min Act: -0.0001
Data Index: 1081910 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.2109. Min Act: -0.0001
Data Index: 1294554 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.1213. Min Act: -0.0001
Data Index: 345493 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.1520. Min Act: -0.0001
Data Index: 580136 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0682. Min Act: -0.0001
Data Index: 833282 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0639. Min Act: -0.0001
Data Index: 24137 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0465. Min Act: -0.0001
Data Index: 157315 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0285. Min Act: -0.0001
Data Index: 74884 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0249. Min Act: -0.0001
Data Index: 1118766 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.1469. Min Act: -0.0001
Data Index: 544904 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0063. Min Act: -0.0001
Data Index: 221357 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2685. Min Range: -1.2685
Max Act: 0.9968. Min Act: -0.0001
Data Index: 176640 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2685. Min Range: -1.2685
Max Act: 0.9971. Min Act: -0.0001
Data Index: 19061 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2685. Min Range: -1.2685
Max Act: 0.9934. Min Act: -0.0001
Data Index: 474799 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2685. Min Range: -1.2685
Max Act: 1.0622. Min Act: -0.0001
Data Index: 988904 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2685. Min Range: -1.2685
Max Act: 0.9709. Min Act: -0.0001
Data Index: 1525978 (Python Code)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2685. Min Range: -1.2685
Max Act: 0.9197. Min Act: -0.0001
Data Index: 544968 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2685. Min Range: -1.2685
Max Act: 0.9924. Min Act: -0.0001
Data Index: 28624 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19