Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2226 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.5744. Min Act: -0.0001
Data Index: 325721 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.4547. Min Act: -0.0001
Data Index: 1466902 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.5059. Min Act: -0.0001
Data Index: 1647530 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.4809. Min Act: -0.0001
Data Index: 1651588 (Python Code)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.4517. Min Act: -0.0001
Data Index: 1501504 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2520. Min Act: -0.0001
Data Index: 1525216 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.3713. Min Act: -0.0001
Data Index: 1452015 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.3620. Min Act: -0.0001
Data Index: 1533718 (Python Code)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2892. Min Act: -0.0001
Data Index: 1519072 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2473. Min Act: -0.0001
Data Index: 1364991 (Python Code)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2132. Min Act: -0.0001
Data Index: 1632464 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.3268. Min Act: -0.0001
Data Index: 1465173 (Python Code)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2690. Min Act: -0.0001
Data Index: 1360021 (Python Code)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2373. Min Act: -0.0001
Data Index: 918198 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2223. Min Act: -0.0001
Data Index: 699763 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2522. Min Act: -0.0001
Data Index: 1580748 (Python Code)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.1978. Min Act: -0.0001
Data Index: 1563373 (Python Code)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2112. Min Act: -0.0001
Data Index: 916436 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2320. Min Act: -0.0001
Data Index: 883916 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5744. Min Range: -1.5744
Max Act: 1.2341. Min Act: -0.0001
Data Index: 1548870 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19