Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2617 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.8840. Min Act: -0.0001
Data Index: 1218343 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.5450. Min Act: -0.0001
Data Index: 231426 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.5635. Min Act: -0.0001
Data Index: 996619 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.4733. Min Act: -0.0001
Data Index: 1172548 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.4660. Min Act: -0.0001
Data Index: 471059 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3651. Min Act: -0.0001
Data Index: 615516 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.4254. Min Act: -0.0001
Data Index: 911371 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3587. Min Act: -0.0001
Data Index: 1213044 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3458. Min Act: -0.0001
Data Index: 202231 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.4580. Min Act: -0.0001
Data Index: 78098 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.2499. Min Act: -0.0001
Data Index: 1316636 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.1741. Min Act: -0.0001
Data Index: 120093 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.4543. Min Act: -0.0001
Data Index: 1171719 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3823. Min Act: -0.0001
Data Index: 1338819 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3412. Min Act: -0.0001
Data Index: 1300281 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.4395. Min Act: -0.0001
Data Index: 402363 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3568. Min Act: -0.0001
Data Index: 512246 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3608. Min Act: -0.0001
Data Index: 388989 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.3471. Min Act: -0.0001
Data Index: 1278710 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8840. Min Range: -1.8840
Max Act: 1.2821. Min Act: -0.0001
Data Index: 1237542 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19