Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2507 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.7276. Min Act: -0.0001
Data Index: 80732 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6692. Min Act: -0.0001
Data Index: 339516 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.7028. Min Act: -0.0001
Data Index: 733297 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6946. Min Act: -0.0001
Data Index: 497397 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6025. Min Act: -0.0001
Data Index: 1078586 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6151. Min Act: -0.0001
Data Index: 1048627 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6372. Min Act: -0.0001
Data Index: 426608 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6353. Min Act: -0.0001
Data Index: 1046974 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.7093. Min Act: -0.0001
Data Index: 1289397 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6137. Min Act: -0.0001
Data Index: 138422 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6198. Min Act: -0.0001
Data Index: 930898 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.6134. Min Act: -0.0001
Data Index: 677834 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5897. Min Act: -0.0001
Data Index: 113168 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5764. Min Act: -0.0001
Data Index: 493354 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5611. Min Act: -0.0001
Data Index: 427156 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5824. Min Act: -0.0001
Data Index: 1116121 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5672. Min Act: -0.0001
Data Index: 42294 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5498. Min Act: -0.0001
Data Index: 335381 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5856. Min Act: -0.0001
Data Index: 446436 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7276. Min Range: -0.7276
Max Act: 0.5729. Min Act: -0.0001
Data Index: 1099735 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19