Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4204 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.8166. Min Act: -0.0001
Data Index: 718721 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.5550. Min Act: -0.0001
Data Index: 315514 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.1445. Min Act: -0.0001
Data Index: 1020468 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.2491. Min Act: -0.0001
Data Index: 1120897 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.3234. Min Act: -0.0001
Data Index: 720006 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.3036. Min Act: -0.0001
Data Index: 556618 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8166. Min Range: -2.8166
Max Act: 1.9451. Min Act: -0.0001
Data Index: 813886 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.2199. Min Act: -0.0001
Data Index: 385566 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.2054. Min Act: -0.0001
Data Index: 1030991 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.0749. Min Act: -0.0001
Data Index: 543970 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.2256. Min Act: -0.0001
Data Index: 362063 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.1166. Min Act: -0.0001
Data Index: 933384 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.1279. Min Act: -0.0001
Data Index: 211568 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.1093. Min Act: -0.0001
Data Index: 1004555 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.1806. Min Act: -0.0001
Data Index: 672930 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.0492. Min Act: -0.0001
Data Index: 902854 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.0615. Min Act: -0.0001
Data Index: 757499 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.0326. Min Act: -0.0001
Data Index: 524558 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.0292. Min Act: -0.0001
Data Index: 192310 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8166. Min Range: -2.8166
Max Act: 2.0047. Min Act: -0.0001
Data Index: 31851 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19