Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3743 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4804. Min Range: -1.4804
Max Act: 1.4804. Min Act: -0.0001
Data Index: 1107878 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4804. Min Range: -1.4804
Max Act: 1.1187. Min Act: -0.0001
Data Index: 1343112 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4804. Min Range: -1.4804
Max Act: 1.0650. Min Act: -0.0001
Data Index: 588249 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4804. Min Range: -1.4804
Max Act: 1.0630. Min Act: -0.0001
Data Index: 996639 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4804. Min Range: -1.4804
Max Act: 1.0431. Min Act: -0.0001
Data Index: 259135 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9852. Min Act: -0.0001
Data Index: 1434815 (Python Code)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4804. Min Range: -1.4804
Max Act: 1.0559. Min Act: -0.0001
Data Index: 1315284 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9537. Min Act: -0.0001
Data Index: 556776 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9565. Min Act: -0.0001
Data Index: 431015 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4804. Min Range: -1.4804
Max Act: 1.0020. Min Act: -0.0001
Data Index: 863543 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9162. Min Act: -0.0001
Data Index: 1187974 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9077. Min Act: -0.0001
Data Index: 123822 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.8472. Min Act: -0.0001
Data Index: 582112 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9109. Min Act: -0.0001
Data Index: 166740 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.8250. Min Act: -0.0001
Data Index: 312793 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9088. Min Act: -0.0001
Data Index: 1365388 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.8791. Min Act: -0.0001
Data Index: 1040992 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.8173. Min Act: -0.0001
Data Index: 1051212 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.9210. Min Act: -0.0001
Data Index: 235582 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4804. Min Range: -1.4804
Max Act: 0.8649. Min Act: -0.0001
Data Index: 1085976 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19