Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3691 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.4956. Min Act: -0.0001
Data Index: 1224273 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.3744. Min Act: -0.0001
Data Index: 1310940 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.3726. Min Act: -0.0001
Data Index: 1208664 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.4382. Min Act: -0.0001
Data Index: 253490 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.2461. Min Act: -0.0001
Data Index: 1334987 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.1958. Min Act: -0.0001
Data Index: 194752 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.2082. Min Act: -0.0001
Data Index: 1261090 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.2399. Min Act: -0.0001
Data Index: 998183 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.1552. Min Act: -0.0001
Data Index: 1338596 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.1380. Min Act: -0.0001
Data Index: 876726 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.0682. Min Act: -0.0001
Data Index: 170634 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4956. Min Range: -1.4956
Max Act: 0.9685. Min Act: -0.0001
Data Index: 941975 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.0328. Min Act: -0.0001
Data Index: 1176110 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.0251. Min Act: -0.0001
Data Index: 1616809 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4956. Min Range: -1.4956
Max Act: 0.9237. Min Act: -0.0001
Data Index: 1589012 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4956. Min Range: -1.4956
Max Act: 0.9730. Min Act: -0.0001
Data Index: 1372956 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4956. Min Range: -1.4956
Max Act: 1.0003. Min Act: -0.0001
Data Index: 563630 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4956. Min Range: -1.4956
Max Act: 0.9704. Min Act: -0.0001
Data Index: 1625957 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4956. Min Range: -1.4956
Max Act: 0.9339. Min Act: -0.0001
Data Index: 1520697 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4956. Min Range: -1.4956
Max Act: 0.9030. Min Act: -0.0001
Data Index: 1641700 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19