Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3243 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.6994. Min Act: -0.0001
Data Index: 77029 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.6827. Min Act: -0.0001
Data Index: 864256 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.4946. Min Act: -0.0001
Data Index: 149940 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0404. Min Range: -6.0404
Max Act: 6.0174. Min Act: -0.0001
Data Index: 1136464 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.8002. Min Act: -0.0001
Data Index: 516715 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.8694. Min Act: -0.0001
Data Index: 684488 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.6756. Min Act: -0.0001
Data Index: 1294205 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.6897. Min Act: -0.0001
Data Index: 206793 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.6494. Min Act: -0.0001
Data Index: 1101361 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.4937. Min Act: -0.0001
Data Index: 198224 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.4911. Min Act: -0.0001
Data Index: 913551 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.6253. Min Act: -0.0001
Data Index: 20520 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.5645. Min Act: -0.0001
Data Index: 1008124 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.5405. Min Act: -0.0001
Data Index: 210519 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0404. Min Range: -6.0404
Max Act: 6.0404. Min Act: -0.0001
Data Index: 1142715 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.3891. Min Act: -0.0001
Data Index: 1346988 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.3578. Min Act: -0.0001
Data Index: 1025232 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.3597. Min Act: -0.0001
Data Index: 673082 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.3265. Min Act: -0.0001
Data Index: 331463 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0404. Min Range: -6.0404
Max Act: 5.2993. Min Act: -0.0001
Data Index: 975091 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19