Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 350 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3727. Min Act: -0.0001
Data Index: 352560 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3704. Min Act: -0.0001
Data Index: 453866 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3583. Min Act: -0.0001
Data Index: 1385233 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3551. Min Act: -0.0001
Data Index: 1351121 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3535. Min Act: -0.0001
Data Index: 708165 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3300. Min Act: -0.0001
Data Index: 749340 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3096. Min Act: -0.0001
Data Index: 1102004 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3493. Min Act: -0.0001
Data Index: 1481562 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3378. Min Act: -0.0001
Data Index: 1181608 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3207. Min Act: -0.0001
Data Index: 280062 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3428. Min Act: -0.0001
Data Index: 939958 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3342. Min Act: -0.0001
Data Index: 723106 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3045. Min Act: -0.0001
Data Index: 1205582 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3271. Min Act: -0.0001
Data Index: 1146876 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3235. Min Act: -0.0001
Data Index: 715560 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3085. Min Act: -0.0001
Data Index: 1128352 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.3071. Min Act: -0.0001
Data Index: 743744 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.2940. Min Act: -0.0001
Data Index: 1266583 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.2802. Min Act: -0.0000
Data Index: 41866 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3727. Min Range: -0.3727
Max Act: 0.2988. Min Act: -0.0001
Data Index: 984400 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19