Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 940 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.2026. Min Act: -0.0000
Data Index: 1110235 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.6915. Min Act: -0.0000
Data Index: 321983 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.7512. Min Act: -0.0000
Data Index: 551123 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.4810. Min Act: -0.0000
Data Index: 1077427 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.3614. Min Act: -0.0000
Data Index: 267931 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.2057. Min Act: -0.0000
Data Index: 335908 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.3137. Min Act: -0.0000
Data Index: 397301 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.0745. Min Act: -0.0000
Data Index: 737804 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.7322. Min Act: -0.0000
Data Index: 530765 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.5954. Min Act: -0.0000
Data Index: 328294 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.1675. Min Act: -0.0000
Data Index: 165165 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.2957. Min Act: -0.0000
Data Index: 220166 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.2228. Min Act: -0.0000
Data Index: 1468568 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.1112. Min Act: -0.0000
Data Index: 151350 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.1075. Min Act: -0.0000
Data Index: 591328 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2026. Min Range: -5.2026
Max Act: 2.9583. Min Act: -0.0000
Data Index: 782791 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.0825. Min Act: -0.0000
Data Index: 769992 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.0560. Min Act: -0.0000
Data Index: 1294987 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2026. Min Range: -5.2026
Max Act: 2.8798. Min Act: -0.0000
Data Index: 158968 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2026. Min Range: -5.2026
Max Act: 3.0199. Min Act: -0.0000
Data Index: 653028 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19