Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2986 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.3623. Min Act: -0.0001
Data Index: 1589104 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1931. Min Act: -0.0001
Data Index: 1524540 (Python Code)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.2878. Min Act: -0.0001
Data Index: 1612811 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.2319. Min Act: -0.0001
Data Index: 1379906 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.2161. Min Act: -0.0001
Data Index: 1556600 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1029. Min Act: -0.0001
Data Index: 1503218 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.2110. Min Act: -0.0001
Data Index: 1581139 (Python Code)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1709. Min Act: -0.0001
Data Index: 1396189 (Python Code)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1372. Min Act: -0.0001
Data Index: 1452907 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1316. Min Act: -0.0001
Data Index: 1374611 (Python Code)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1301. Min Act: -0.0001
Data Index: 1378184 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1748. Min Act: -0.0001
Data Index: 1362962 (Python Code)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1435. Min Act: -0.0001
Data Index: 1553060 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.0925. Min Act: -0.0001
Data Index: 1391625 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.0589. Min Act: -0.0001
Data Index: 1579442 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1259. Min Act: -0.0001
Data Index: 1520015 (Python Code)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.0595. Min Act: -0.0001
Data Index: 1566927 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1263. Min Act: -0.0001
Data Index: 1391344 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1156. Min Act: -0.0001
Data Index: 1434414 (Python Code)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3623. Min Range: -1.3623
Max Act: 1.1112. Min Act: -0.0001
Data Index: 1569504 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19