Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2598 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.3315. Min Act: -0.0001
Data Index: 1589348 (Python Code)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1960. Min Act: -0.0001
Data Index: 1384068 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.3824. Min Act: -0.0001
Data Index: 1441306 (Python Code)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.2441. Min Act: -0.0001
Data Index: 1420540 (Python Code)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1860. Min Act: -0.0001
Data Index: 792424 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.3514. Min Act: -0.0001
Data Index: 1488275 (Python Code)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1245. Min Act: -0.0001
Data Index: 1485203 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1011. Min Act: -0.0001
Data Index: 1432076 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1054. Min Act: -0.0001
Data Index: 1589754 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1251. Min Act: -0.0001
Data Index: 68878 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.0732. Min Act: -0.0001
Data Index: 1444156 (Python Code)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1082. Min Act: -0.0001
Data Index: 1630018 (Python Code)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.0688. Min Act: -0.0001
Data Index: 1379883 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1226. Min Act: -0.0001
Data Index: 911247 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.0837. Min Act: -0.0001
Data Index: 1239909 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.0151. Min Act: -0.0001
Data Index: 1506239 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.0805. Min Act: -0.0001
Data Index: 1586165 (Python Code)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.1093. Min Act: -0.0001
Data Index: 751088 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3824. Min Range: -1.3824
Max Act: 0.9743. Min Act: -0.0001
Data Index: 1451643 (Python Code)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3824. Min Range: -1.3824
Max Act: 1.0010. Min Act: -0.0001
Data Index: 1648474 (Python Code)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19