Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2898 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1998. Min Range: -2.1998
Max Act: 2.1998. Min Act: -0.0001
Data Index: 1452581 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.9192. Min Act: -0.0001
Data Index: 1476977 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.7723. Min Act: -0.0001
Data Index: 1514419 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.7247. Min Act: -0.0000
Data Index: 1549876 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.7097. Min Act: -0.0001
Data Index: 1608926 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.6186. Min Act: -0.0001
Data Index: 1435137 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.6385. Min Act: -0.0001
Data Index: 176281 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.5621. Min Act: -0.0001
Data Index: 1458431 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.6249. Min Act: -0.0001
Data Index: 1587017 (Python Code)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.5229. Min Act: -0.0001
Data Index: 1619272 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.5201. Min Act: -0.0001
Data Index: 1566446 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.6635. Min Act: -0.0001
Data Index: 1374875 (Python Code)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.4736. Min Act: -0.0001
Data Index: 1621989 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.5911. Min Act: -0.0001
Data Index: 1454557 (Python Code)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.4933. Min Act: -0.0001
Data Index: 1390334 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.5198. Min Act: -0.0001
Data Index: 1438250 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.4356. Min Act: -0.0000
Data Index: 1441254 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.4330. Min Act: -0.0001
Data Index: 1591272 (Python Code)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.4146. Min Act: -0.0001
Data Index: 1446584 (Python Code)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1998. Min Range: -2.1998
Max Act: 1.4547. Min Act: -0.0001
Data Index: 1618752 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19