Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1747 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4670. Min Range: -2.4670
Max Act: 2.4670. Min Act: -0.0001
Data Index: 114563 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4670. Min Range: -2.4670
Max Act: 2.1090. Min Act: -0.0001
Data Index: 493661 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.9555. Min Act: -0.0001
Data Index: 1390369 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8310. Min Act: -0.0001
Data Index: 1437723 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.7371. Min Act: -0.0001
Data Index: 233665 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4670. Min Range: -2.4670
Max Act: 2.0662. Min Act: -0.0001
Data Index: 928180 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.9454. Min Act: -0.0001
Data Index: 1435642 (Python Code)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8524. Min Act: -0.0001
Data Index: 138799 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4670. Min Range: -2.4670
Max Act: 2.0529. Min Act: -0.0001
Data Index: 1636128 (Python Code)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8345. Min Act: -0.0001
Data Index: 1524359 (Python Code)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8126. Min Act: -0.0001
Data Index: 209675 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4670. Min Range: -2.4670
Max Act: 2.0291. Min Act: -0.0001
Data Index: 779284 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4670. Min Range: -2.4670
Max Act: 2.1201. Min Act: -0.0001
Data Index: 1647853 (Python Code)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4670. Min Range: -2.4670
Max Act: 2.1296. Min Act: -0.0001
Data Index: 689340 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8235. Min Act: -0.0001
Data Index: 418074 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.7812. Min Act: -0.0001
Data Index: 1128400 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8534. Min Act: -0.0001
Data Index: 65660 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.9632. Min Act: -0.0001
Data Index: 1532499 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8630. Min Act: -0.0001
Data Index: 988363 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4670. Min Range: -2.4670
Max Act: 1.8487. Min Act: -0.0001
Data Index: 1553902 (Python Code)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19