Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3650 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.8289. Min Act: -0.0001
Data Index: 213204 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.9071. Min Act: -0.0001
Data Index: 828464 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.7098. Min Act: -0.0001
Data Index: 922061 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.5862. Min Act: -0.0001
Data Index: 1308464 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.5424. Min Act: -0.0001
Data Index: 805428 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.4125. Min Act: -0.0001
Data Index: 754082 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.4505. Min Act: -0.0001
Data Index: 1315587 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.4156. Min Act: -0.0001
Data Index: 326686 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.5003. Min Act: -0.0001
Data Index: 343041 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.3784. Min Act: -0.0001
Data Index: 898704 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.2584. Min Act: -0.0001
Data Index: 1098628 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.2907. Min Act: -0.0001
Data Index: 675072 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.3220. Min Act: -0.0001
Data Index: 612221 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.2026. Min Act: -0.0001
Data Index: 884762 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.2387. Min Act: -0.0001
Data Index: 324193 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.3286. Min Act: -0.0001
Data Index: 930830 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.1518. Min Act: -0.0001
Data Index: 1071876 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.2105. Min Act: -0.0001
Data Index: 549102 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.2718. Min Act: -0.0001
Data Index: 1333007 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9071. Min Range: -1.9071
Max Act: 1.2033. Min Act: -0.0001
Data Index: 973170 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19