Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3426 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.5112. Min Act: -0.0001
Data Index: 537015 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4517. Min Act: -0.0001
Data Index: 1590996 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4428. Min Act: -0.0001
Data Index: 1433951 (Python Code)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4154. Min Act: -0.0001
Data Index: 1470778 (Python Code)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4671. Min Act: -0.0001
Data Index: 1565055 (Python Code)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4642. Min Act: -0.0001
Data Index: 1548336 (Python Code)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4639. Min Act: -0.0001
Data Index: 1546077 (Python Code)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4213. Min Act: -0.0001
Data Index: 1505625 (Python Code)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4112. Min Act: -0.0001
Data Index: 1481476 (Python Code)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4301. Min Act: -0.0001
Data Index: 1510636 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4130. Min Act: -0.0001
Data Index: 1385034 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4038. Min Act: -0.0001
Data Index: 1382910 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.3706. Min Act: -0.0001
Data Index: 1574655 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.3904. Min Act: -0.0001
Data Index: 1440092 (Python Code)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.3751. Min Act: -0.0001
Data Index: 1093407 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.3735. Min Act: -0.0001
Data Index: 1524629 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.3468. Min Act: -0.0001
Data Index: 1366349 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.3596. Min Act: -0.0001
Data Index: 1348666 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.4050. Min Act: -0.0001
Data Index: 582157 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5112. Min Range: -0.5112
Max Act: 0.3566. Min Act: -0.0001
Data Index: 1596810 (Python Code)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19