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

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

Neuron 3823 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1246. Min Range: -2.1246

Max Act: 2.1246. Min Act: -0.0000

Data Index: 346643 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 2.1246. Min Range: -2.1246

Max Act: 2.0933. Min Act: -0.0000

Data Index: 874169 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.7347. Min Act: -0.0000

Data Index: 1249217 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.8100. Min Act: -0.0000

Data Index: 403237 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5978. Min Act: -0.0000

Data Index: 1012849 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.7670. Min Act: -0.0000

Data Index: 765087 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.6188. Min Act: -0.0000

Data Index: 841635 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.6205. Min Act: -0.0000

Data Index: 70398 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.6879. Min Act: -0.0000

Data Index: 776036 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.6477. Min Act: -0.0000

Data Index: 502356 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5369. Min Act: -0.0000

Data Index: 364124 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.6966. Min Act: -0.0000

Data Index: 399392 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.7779. Min Act: -0.0000

Data Index: 1306159 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.4699. Min Act: -0.0000

Data Index: 799905 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5831. Min Act: -0.0000

Data Index: 1236913 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1140019 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5436. Min Act: -0.0000

Data Index: 1137458 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.5585. Min Act: -0.0000

Data Index: 711219 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1071537 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 2.1246. Min Range: -2.1246

Max Act: 1.4681. Min Act: -0.0000

Data Index: 305979 (C4 (Web Text))

Max Activating Token Index: 689