Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3794 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.9247. Min Act: -0.0001
Data Index: 269419 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.7640. Min Act: -0.0001
Data Index: 1329178 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.5937. Min Act: -0.0001
Data Index: 1315002 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.4167. Min Act: -0.0001
Data Index: 691393 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.7807. Min Act: -0.0001
Data Index: 549626 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.7946. Min Act: -0.0001
Data Index: 741565 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.2281. Min Act: -0.0001
Data Index: 69 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.3035. Min Act: -0.0001
Data Index: 875675 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.6353. Min Act: -0.0001
Data Index: 533651 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.5573. Min Act: -0.0001
Data Index: 587374 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.3655. Min Act: -0.0001
Data Index: 769465 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.2932. Min Act: -0.0001
Data Index: 238332 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.2977. Min Act: -0.0001
Data Index: 1223544 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.1677. Min Act: -0.0001
Data Index: 1203474 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.2808. Min Act: -0.0001
Data Index: 1146723 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.1181. Min Act: -0.0001
Data Index: 430591 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.2376. Min Act: -0.0001
Data Index: 1281817 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9247. Min Range: -4.9247
Max Act: 3.8141. Min Act: -0.0001
Data Index: 472406 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.2503. Min Act: -0.0001
Data Index: 389526 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9247. Min Range: -4.9247
Max Act: 4.5445. Min Act: -0.0001
Data Index: 783345 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19