Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5612 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.6071. Min Act: -0.0001
Data Index: 874301 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.4357. Min Act: -0.0001
Data Index: 829438 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.4032. Min Act: -0.0001
Data Index: 1077657 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.2645. Min Act: -0.0001
Data Index: 362110 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.3223. Min Act: -0.0001
Data Index: 104323 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.3475. Min Act: -0.0001
Data Index: 1286186 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.2330. Min Act: -0.0001
Data Index: 826865 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.3135. Min Act: -0.0001
Data Index: 134129 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.2052. Min Act: -0.0001
Data Index: 526593 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.1449. Min Act: -0.0001
Data Index: 796813 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.1812. Min Act: -0.0001
Data Index: 777264 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.1862. Min Act: -0.0001
Data Index: 911442 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.0994. Min Act: -0.0001
Data Index: 272202 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.1425. Min Act: -0.0001
Data Index: 89886 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.1395. Min Act: -0.0001
Data Index: 759687 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.1230. Min Act: -0.0001
Data Index: 511491 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.0727. Min Act: -0.0001
Data Index: 665928 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.0859. Min Act: -0.0001
Data Index: 1199037 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.0790. Min Act: -0.0001
Data Index: 122635 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6071. Min Range: -1.6071
Max Act: 1.0348. Min Act: -0.0001
Data Index: 612480 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19