Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1289 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0773. Min Range: -2.0773
Max Act: 2.0773. Min Act: -0.0001
Data Index: 633896 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.8313. Min Act: -0.0001
Data Index: 1135793 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.7452. Min Act: -0.0001
Data Index: 569721 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.7384. Min Act: -0.0001
Data Index: 1132936 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5487. Min Act: -0.0001
Data Index: 1359205 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.6498. Min Act: -0.0001
Data Index: 1247723 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.7930. Min Act: -0.0001
Data Index: 62938 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5953. Min Act: -0.0001
Data Index: 449467 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.7503. Min Act: -0.0001
Data Index: 513345 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.6272. Min Act: -0.0001
Data Index: 167479 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.7366. Min Act: -0.0001
Data Index: 1630820 (Python Code)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5294. Min Act: -0.0001
Data Index: 214078 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.6156. Min Act: -0.0001
Data Index: 38719 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5659. Min Act: -0.0001
Data Index: 1075261 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5890. Min Act: -0.0000
Data Index: 1641893 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5537. Min Act: -0.0001
Data Index: 937416 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.4668. Min Act: -0.0001
Data Index: 897193 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5472. Min Act: -0.0001
Data Index: 242839 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.6749. Min Act: -0.0001
Data Index: 489808 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0773. Min Range: -2.0773
Max Act: 1.5465. Min Act: -0.0001
Data Index: 166950 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19