Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 47 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.4306. Min Act: -0.0001
Data Index: 92558 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.4728. Min Act: -0.0001
Data Index: 1006034 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.4981. Min Act: -0.0001
Data Index: 1538391 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.3915. Min Act: -0.0001
Data Index: 1302497 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.3481. Min Act: -0.0001
Data Index: 1506158 (Python Code)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2615. Min Act: -0.0001
Data Index: 632188 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.3637. Min Act: -0.0001
Data Index: 518405 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2982. Min Act: -0.0001
Data Index: 418971 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2640. Min Act: -0.0001
Data Index: 1209214 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2817. Min Act: -0.0001
Data Index: 1533806 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2737. Min Act: -0.0001
Data Index: 870838 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.3322. Min Act: -0.0001
Data Index: 1510268 (Python Code)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.1710. Min Act: -0.0001
Data Index: 477205 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.3634. Min Act: -0.0001
Data Index: 659888 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2390. Min Act: -0.0001
Data Index: 251731 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.3012. Min Act: -0.0001
Data Index: 543354 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2650. Min Act: -0.0001
Data Index: 1392224 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2672. Min Act: -0.0001
Data Index: 332275 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2463. Min Act: -0.0001
Data Index: 1410448 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4981. Min Range: -1.4981
Max Act: 1.2712. Min Act: -0.0001
Data Index: 846722 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19