Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2445 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.8301. Min Act: -0.0001
Data Index: 1369862 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.6825. Min Act: -0.0001
Data Index: 1363669 (Python Code)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.5912. Min Act: -0.0001
Data Index: 1415240 (Python Code)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.4450. Min Act: -0.0001
Data Index: 1570688 (Python Code)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.4697. Min Act: -0.0001
Data Index: 1418741 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.4790. Min Act: -0.0001
Data Index: 1517920 (Python Code)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.4876. Min Act: -0.0001
Data Index: 1487555 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.3818. Min Act: -0.0001
Data Index: 1366293 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.2678. Min Act: -0.0001
Data Index: 1384463 (Python Code)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.4212. Min Act: -0.0001
Data Index: 1607935 (Python Code)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.3302. Min Act: -0.0001
Data Index: 1655345 (Python Code)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.4291. Min Act: -0.0001
Data Index: 1583193 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.1917. Min Act: -0.0001
Data Index: 1598305 (Python Code)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.3561. Min Act: -0.0001
Data Index: 1364289 (Python Code)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.3107. Min Act: -0.0001
Data Index: 1542751 (Python Code)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.3705. Min Act: -0.0001
Data Index: 1427822 (Python Code)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.3268. Min Act: -0.0001
Data Index: 1597393 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.3972. Min Act: -0.0001
Data Index: 1619980 (Python Code)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.2465. Min Act: -0.0001
Data Index: 1543188 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8301. Min Range: -1.8301
Max Act: 1.4831. Min Act: -0.0001
Data Index: 1553532 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19