Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3847 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.8330. Min Act: -0.0001
Data Index: 591664 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.7766. Min Act: -0.0001
Data Index: 120044 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.8048. Min Act: -0.0001
Data Index: 1286646 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.7983. Min Act: -0.0001
Data Index: 766706 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.7627. Min Act: -0.0001
Data Index: 142237 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.7682. Min Act: -0.0001
Data Index: 80752 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.8646. Min Act: -0.0001
Data Index: 746114 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.6968. Min Act: -0.0001
Data Index: 1204837 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.7282. Min Act: -0.0001
Data Index: 487370 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.5873. Min Act: -0.0001
Data Index: 321675 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.5186. Min Act: -0.0001
Data Index: 340492 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.6849. Min Act: -0.0001
Data Index: 1289939 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.4664. Min Act: -0.0001
Data Index: 333830 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.4526. Min Act: -0.0001
Data Index: 365162 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.4657. Min Act: -0.0001
Data Index: 542781 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.3960. Min Act: -0.0002
Data Index: 297654 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.4736. Min Act: -0.0001
Data Index: 1021383 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.3717. Min Act: -0.0001
Data Index: 794263 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.2051. Min Act: -0.0001
Data Index: 222446 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8646. Min Range: -1.8646
Max Act: 1.3442. Min Act: -0.0001
Data Index: 717600 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19