Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3165 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.8284. Min Act: -0.0001
Data Index: 1239579 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.8782. Min Act: -0.0001
Data Index: 877560 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.7868. Min Act: -0.0001
Data Index: 1291407 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.6382. Min Act: -0.0001
Data Index: 1315772 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.6516. Min Act: -0.0001
Data Index: 208667 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.6731. Min Act: -0.0001
Data Index: 764916 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.6432. Min Act: -0.0001
Data Index: 280886 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5664. Min Act: -0.0001
Data Index: 1313470 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.6630. Min Act: -0.0001
Data Index: 959806 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.6142. Min Act: -0.0001
Data Index: 752094 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5079. Min Act: -0.0001
Data Index: 944572 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5752. Min Act: -0.0001
Data Index: 250707 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5600. Min Act: -0.0001
Data Index: 401567 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5630. Min Act: -0.0001
Data Index: 1039734 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5954. Min Act: -0.0001
Data Index: 1352264 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5728. Min Act: -0.0001
Data Index: 703778 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5709. Min Act: -0.0001
Data Index: 1106099 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5532. Min Act: -0.0001
Data Index: 667842 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5130. Min Act: -0.0000
Data Index: 192463 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8782. Min Range: -0.8782
Max Act: 0.5190. Min Act: -0.0001
Data Index: 591205 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19