Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2005 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.4529. Min Range: -2.4529
Max Act: 2.4529. Min Act: -0.0001
Data Index: 424507 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4529. Min Range: -2.4529
Max Act: 2.0856. Min Act: -0.0001
Data Index: 1212112 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4529. Min Range: -2.4529
Max Act: 2.0654. Min Act: -0.0001
Data Index: 1241611 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4529. Min Range: -2.4529
Max Act: 2.0588. Min Act: -0.0001
Data Index: 895888 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4529. Min Range: -2.4529
Max Act: 2.0824. Min Act: -0.0001
Data Index: 1273218 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.9897. Min Act: -0.0001
Data Index: 1100896 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4529. Min Range: -2.4529
Max Act: 2.1077. Min Act: -0.0001
Data Index: 1020860 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4529. Min Range: -2.4529
Max Act: 2.0123. Min Act: -0.0001
Data Index: 827425 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.8326. Min Act: -0.0001
Data Index: 275333 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.6819. Min Act: -0.0001
Data Index: 185169 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.7665. Min Act: -0.0001
Data Index: 1200916 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.8074. Min Act: -0.0001
Data Index: 267764 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.8355. Min Act: -0.0001
Data Index: 900526 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.6339. Min Act: -0.0001
Data Index: 87935 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.7708. Min Act: -0.0001
Data Index: 467884 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.7038. Min Act: -0.0001
Data Index: 302002 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.7462. Min Act: -0.0001
Data Index: 838639 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.5611. Min Act: -0.0001
Data Index: 243940 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.6517. Min Act: -0.0001
Data Index: 36655 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4529. Min Range: -2.4529
Max Act: 1.5825. Min Act: -0.0001
Data Index: 59247 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19