Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1133 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3503. Min Act: -0.0000

Data Index: 756004 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3211. Min Act: -0.0000

Data Index: 482190 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3124. Min Act: -0.0000

Data Index: 783197 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3056. Min Act: -0.0000

Data Index: 477993 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.3043. Min Act: -0.0000

Data Index: 425003 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1173081 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2689. Min Act: -0.0000

Data Index: 520239 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2574. Min Act: -0.0000

Data Index: 1227482 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.1676. Min Act: -0.0000

Data Index: 987865 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.1351. Min Act: -0.0000

Data Index: 1256828 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.2180. Min Act: -0.0000

Data Index: 826735 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1103823 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.1056. Min Act: -0.0000

Data Index: 1304827 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0732. Min Act: -0.0000

Data Index: 875620 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1102593 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0223. Min Act: -0.0000

Data Index: 831836 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9926. Min Act: -0.0000

Data Index: 111098 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.3503. Min Range: -1.3503

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1335572 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9425. Min Act: -0.0000

Data Index: 803413 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.3503. Min Range: -1.3503

Max Act: 0.9894. Min Act: -0.0000

Data Index: 1246929 (C4 (Web Text))

Max Activating Token Index: 431