Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2193 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.7404. Min Act: -0.0001
Data Index: 782532 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.4608. Min Act: -0.0001
Data Index: 563678 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.2921. Min Act: -0.0001
Data Index: 1285327 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.4368. Min Act: -0.0001
Data Index: 488380 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.1305. Min Act: -0.0001
Data Index: 246383 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.4279. Min Act: -0.0001
Data Index: 554566 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.0317. Min Act: -0.0001
Data Index: 536075 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.9877. Min Act: -0.0001
Data Index: 749323 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.9728. Min Act: -0.0001
Data Index: 1223170 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.8051. Min Act: -0.0001
Data Index: 152984 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.6264. Min Act: -0.0001
Data Index: 645346 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.1068. Min Act: -0.0001
Data Index: 292796 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.0828. Min Act: -0.0001
Data Index: 853297 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.5891. Min Act: -0.0001
Data Index: 621637 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.8889. Min Act: -0.0001
Data Index: 194498 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.0393. Min Act: -0.0001
Data Index: 18178 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.8159. Min Act: -0.0001
Data Index: 1296067 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.8211. Min Act: -0.0001
Data Index: 95584 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7404. Min Range: -4.7404
Max Act: 4.0336. Min Act: -0.0001
Data Index: 899692 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7404. Min Range: -4.7404
Max Act: 3.8228. Min Act: -0.0001
Data Index: 646782 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19