Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2561 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5830. Min Range: -2.5830
Max Act: 2.5830. Min Act: -0.0001
Data Index: 316649 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5830. Min Range: -2.5830
Max Act: 2.0586. Min Act: -0.0001
Data Index: 46839 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.9351. Min Act: -0.0001
Data Index: 66109 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.9613. Min Act: -0.0001
Data Index: 638359 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.8437. Min Act: -0.0001
Data Index: 189357 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.9803. Min Act: -0.0001
Data Index: 1232635 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.7441. Min Act: -0.0001
Data Index: 716581 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.8707. Min Act: -0.0001
Data Index: 445411 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.7669. Min Act: -0.0001
Data Index: 372367 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.9455. Min Act: -0.0001
Data Index: 213542 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.8535. Min Act: -0.0001
Data Index: 107701 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.5493. Min Act: -0.0001
Data Index: 809164 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.7198. Min Act: -0.0001
Data Index: 1116632 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.6957. Min Act: -0.0001
Data Index: 784163 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.5775. Min Act: -0.0001
Data Index: 136923 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.9092. Min Act: -0.0001
Data Index: 223715 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.6612. Min Act: -0.0001
Data Index: 1321760 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.7005. Min Act: -0.0001
Data Index: 704991 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.7427. Min Act: -0.0001
Data Index: 1241261 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5830. Min Range: -2.5830
Max Act: 1.6248. Min Act: -0.0001
Data Index: 1290852 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19