Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3575 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.1352. Min Range: -4.1352
Max Act: 4.1352. Min Act: -0.0001
Data Index: 1283125 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1352. Min Range: -4.1352
Max Act: 3.6410. Min Act: -0.0001
Data Index: 975849 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1352. Min Range: -4.1352
Max Act: 3.3554. Min Act: -0.0001
Data Index: 261520 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1352. Min Range: -4.1352
Max Act: 3.1361. Min Act: -0.0001
Data Index: 690575 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1352. Min Range: -4.1352
Max Act: 3.0506. Min Act: -0.0001
Data Index: 846400 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.9138. Min Act: -0.0001
Data Index: 532502 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.9084. Min Act: -0.0001
Data Index: 1199715 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1352. Min Range: -4.1352
Max Act: 3.0315. Min Act: -0.0001
Data Index: 1294336 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.8812. Min Act: -0.0001
Data Index: 152884 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.7244. Min Act: -0.0001
Data Index: 350048 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.8724. Min Act: -0.0001
Data Index: 128377 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.8716. Min Act: -0.0001
Data Index: 822676 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.7183. Min Act: -0.0001
Data Index: 78133 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.9825. Min Act: -0.0001
Data Index: 120902 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.5362. Min Act: -0.0001
Data Index: 230912 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.9776. Min Act: -0.0001
Data Index: 988710 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.9946. Min Act: -0.0001
Data Index: 679779 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.8329. Min Act: -0.0001
Data Index: 22217 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.4866. Min Act: -0.0001
Data Index: 463137 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1352. Min Range: -4.1352
Max Act: 2.6586. Min Act: -0.0001
Data Index: 108797 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19