Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4038 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.4018. Min Act: -0.0001
Data Index: 1592174 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1926. Min Act: -0.0001
Data Index: 1447066 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.2202. Min Act: -0.0001
Data Index: 1402046 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.2556. Min Act: -0.0001
Data Index: 1486843 (Python Code)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1806. Min Act: -0.0001
Data Index: 1617126 (Python Code)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1460. Min Act: -0.0001
Data Index: 1389255 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1381. Min Act: -0.0001
Data Index: 1497053 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.2016. Min Act: -0.0001
Data Index: 1502971 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1369. Min Act: -0.0001
Data Index: 1402448 (Python Code)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1120. Min Act: -0.0001
Data Index: 1460503 (Python Code)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1226. Min Act: -0.0001
Data Index: 1604493 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.0947. Min Act: -0.0001
Data Index: 1379123 (Python Code)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1465. Min Act: -0.0001
Data Index: 1381262 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1302. Min Act: -0.0001
Data Index: 1475333 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1187. Min Act: -0.0001
Data Index: 1425785 (Python Code)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.0563. Min Act: -0.0001
Data Index: 1589793 (Python Code)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1180. Min Act: -0.0001
Data Index: 1377904 (Python Code)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.1460. Min Act: -0.0001
Data Index: 1526235 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.0474. Min Act: -0.0001
Data Index: 1408972 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4018. Min Range: -1.4018
Max Act: 1.0637. Min Act: -0.0001
Data Index: 1456851 (Python Code)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19