Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3421 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3732. Min Range: -2.3732
Max Act: 2.0401. Min Act: -0.0001
Data Index: 105777 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3732. Min Range: -2.3732
Max Act: 2.0414. Min Act: -0.0001
Data Index: 1256139 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3732. Min Range: -2.3732
Max Act: 2.2528. Min Act: -0.0001
Data Index: 663645 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3732. Min Range: -2.3732
Max Act: 2.3732. Min Act: -0.0001
Data Index: 10738 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3732. Min Range: -2.3732
Max Act: 2.0970. Min Act: -0.0001
Data Index: 777002 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.7960. Min Act: -0.0001
Data Index: 626855 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.8962. Min Act: -0.0001
Data Index: 883361 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.7448. Min Act: -0.0001
Data Index: 424836 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.9187. Min Act: -0.0001
Data Index: 1197711 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.7882. Min Act: -0.0001
Data Index: 159024 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.6840. Min Act: -0.0001
Data Index: 828409 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.7559. Min Act: -0.0001
Data Index: 122589 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.5303. Min Act: -0.0001
Data Index: 202034 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.6996. Min Act: -0.0001
Data Index: 330190 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.6035. Min Act: -0.0001
Data Index: 347819 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.6897. Min Act: -0.0001
Data Index: 617161 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.6758. Min Act: -0.0001
Data Index: 522463 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.6725. Min Act: -0.0001
Data Index: 891509 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.5603. Min Act: -0.0001
Data Index: 93839 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3732. Min Range: -2.3732
Max Act: 1.6605. Min Act: -0.0001
Data Index: 1064568 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19