Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1503 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.9385. Min Act: -0.0001
Data Index: 706415 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.4754. Min Act: -0.0001
Data Index: 724449 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.4362. Min Act: -0.0001
Data Index: 1021139 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.4132. Min Act: -0.0001
Data Index: 35699 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.1885. Min Act: -0.0001
Data Index: 1231922 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.1789. Min Act: -0.0001
Data Index: 562213 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.3599. Min Act: -0.0001
Data Index: 191580 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.1788. Min Act: -0.0001
Data Index: 888389 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.1741. Min Act: -0.0001
Data Index: 1084461 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.0400. Min Act: -0.0001
Data Index: 962490 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9385. Min Range: -2.9385
Max Act: 1.9974. Min Act: -0.0001
Data Index: 525683 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.1235. Min Act: -0.0001
Data Index: 456534 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.0917. Min Act: -0.0001
Data Index: 1180719 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.1023. Min Act: -0.0001
Data Index: 276091 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9385. Min Range: -2.9385
Max Act: 1.9834. Min Act: -0.0001
Data Index: 1086732 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.1460. Min Act: -0.0001
Data Index: 224783 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.0278. Min Act: -0.0001
Data Index: 899058 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.0326. Min Act: -0.0001
Data Index: 810163 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9385. Min Range: -2.9385
Max Act: 2.0027. Min Act: -0.0001
Data Index: 896580 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9385. Min Range: -2.9385
Max Act: 1.9990. Min Act: -0.0001
Data Index: 1052461 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #19