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

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

Neuron 4112 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: 3.8115. Min Range: -3.8115

Max Act: 3.8115. Min Act: -0.0000

Data Index: 886492 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.0369. Min Act: -0.0000

Data Index: 527913 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.0160. Min Act: -0.0000

Data Index: 29337 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.8363. Min Act: -0.0000

Data Index: 175192 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.9703. Min Act: -0.0000

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.9843. Min Act: -0.0000

Data Index: 74441 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.0764. Min Act: -0.0000

Data Index: 68186 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.8781. Min Act: -0.0000

Data Index: 1191169 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.8581. Min Act: -0.0000

Data Index: 681418 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.8650. Min Act: -0.0000

Data Index: 1094248 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.8205. Min Act: -0.0000

Data Index: 1301649 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.6541. Min Act: -0.0000

Data Index: 614932 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.7229. Min Act: -0.0000

Data Index: 362198 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.7890. Min Act: -0.0000

Data Index: 723647 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.8219. Min Act: -0.0000

Data Index: 436205 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.5325. Min Act: -0.0000

Data Index: 611959 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.6427. Min Act: -0.0000

Data Index: 485154 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.7171. Min Act: -0.0000

Data Index: 379507 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.6347. Min Act: -0.0000

Data Index: 544233 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.7175. Min Act: -0.0000

Data Index: 641064 (C4 (Web Text))

Max Activating Token Index: 940