Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2338 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.6331. Min Act: -0.0001
Data Index: 1291820 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.3994. Min Act: -0.0001
Data Index: 1643102 (Python Code)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.3052. Min Act: -0.0001
Data Index: 1574146 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.2059. Min Act: -0.0001
Data Index: 544231 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.2360. Min Act: -0.0001
Data Index: 1443613 (Python Code)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.2388. Min Act: -0.0001
Data Index: 1339609 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1850. Min Act: -0.0001
Data Index: 1115969 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1470. Min Act: -0.0001
Data Index: 1608391 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1353. Min Act: -0.0001
Data Index: 560281 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.2027. Min Act: -0.0001
Data Index: 1135578 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.2019. Min Act: -0.0001
Data Index: 987511 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.2034. Min Act: -0.0001
Data Index: 338376 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1943. Min Act: -0.0001
Data Index: 1084353 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1895. Min Act: -0.0001
Data Index: 1359565 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1511. Min Act: -0.0001
Data Index: 1340170 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1437. Min Act: -0.0001
Data Index: 1415155 (Python Code)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.0894. Min Act: -0.0001
Data Index: 1401379 (Python Code)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1270. Min Act: -0.0001
Data Index: 1285639 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6331. Min Range: -1.6331
Max Act: 1.1021. Min Act: -0.0001
Data Index: 1627267 (Python Code)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6331. Min Range: -1.6331
Max Act: 0.9484. Min Act: -0.0001
Data Index: 477225 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19