Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3653 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.2710. Min Act: -0.0001
Data Index: 1390783 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.4135. Min Act: -0.0001
Data Index: 1601106 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.4643. Min Act: -0.0001
Data Index: 1594974 (Python Code)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.4705. Min Act: -0.0001
Data Index: 535907 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.5651. Min Act: -0.0001
Data Index: 1583187 (Python Code)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.4423. Min Act: -0.0001
Data Index: 1516343 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.3864. Min Act: -0.0001
Data Index: 1523314 (Python Code)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.3036. Min Act: -0.0000
Data Index: 1397740 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.2825. Min Act: -0.0001
Data Index: 1516722 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.4214. Min Act: -0.0001
Data Index: 1592296 (Python Code)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.2925. Min Act: -0.0001
Data Index: 1503924 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.3111. Min Act: -0.0001
Data Index: 765065 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.3692. Min Act: -0.0001
Data Index: 637362 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.3162. Min Act: -0.0001
Data Index: 1381826 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.3169. Min Act: -0.0001
Data Index: 1497472 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.2861. Min Act: -0.0001
Data Index: 1382710 (Python Code)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.2231. Min Act: -0.0001
Data Index: 1579433 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.1176. Min Act: -0.0001
Data Index: 1407972 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.2395. Min Act: -0.0001
Data Index: 156707 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5651. Min Range: -1.5651
Max Act: 1.2264. Min Act: -0.0000
Data Index: 1491860 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19