Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.4731. Min Act: -0.0001

Data Index: 1225990 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.7375. Min Act: -0.0001

Data Index: 883094 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.6523. Min Act: -0.0001

Data Index: 1149544 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.3562. Min Act: -0.0001

Data Index: 968914 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.3150. Min Act: -0.0001

Data Index: 679774 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.2519. Min Act: -0.0001

Data Index: 1234364 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.3032. Min Act: -0.0001

Data Index: 1091479 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.5411. Min Act: -0.0001

Data Index: 237939 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.4765. Min Act: -0.0001

Data Index: 1273788 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.3095. Min Act: -0.0001

Data Index: 1238988 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.1362. Min Act: -0.0001

Data Index: 629462 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.7375. Min Range: -1.7375

Max Act: 0.9154. Min Act: -0.0001

Data Index: 359082 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.0528. Min Act: -0.0001

Data Index: 442319 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.3696. Min Act: -0.0001

Data Index: 681435 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.7375. Min Range: -1.7375

Max Act: 0.9414. Min Act: -0.0001

Data Index: 501788 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.0906. Min Act: -0.0001

Data Index: 373475 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.7375. Min Range: -1.7375

Max Act: 0.9995. Min Act: -0.0001

Data Index: 474741 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.0841. Min Act: -0.0001

Data Index: 823270 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 1.7375. Min Range: -1.7375

Max Act: 1.0924. Min Act: -0.0001

Data Index: 790998 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 1.7375. Min Range: -1.7375

Max Act: 0.9712. Min Act: -0.0001

Data Index: 567270 (C4 (Web Text))

Max Activating Token Index: 930