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

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

Neuron 1505 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1202. Min Range: -2.1202

Max Act: 2.0228. Min Act: -0.0000

Data Index: 1016358 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 2.1202. Min Range: -2.1202

Max Act: 2.1202. Min Act: -0.0001

Data Index: 551386 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.8916. Min Act: -0.0000

Data Index: 14627 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.7105. Min Act: -0.0001

Data Index: 460344 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.8080. Min Act: -0.0001

Data Index: 754191 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.6591. Min Act: -0.0000

Data Index: 290524 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.6927. Min Act: -0.0001

Data Index: 1140640 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1302284 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.2460. Min Act: -0.0001

Data Index: 49037 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.2456. Min Act: -0.0001

Data Index: 246034 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.3069. Min Act: -0.0000

Data Index: 294658 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.1224. Min Act: -0.0001

Data Index: 1337091 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.2474. Min Act: -0.0001

Data Index: 1183237 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.1224. Min Act: -0.0000

Data Index: 565431 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.1580. Min Act: -0.0000

Data Index: 838131 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.1282. Min Act: -0.0001

Data Index: 79679 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.1238. Min Act: -0.0001

Data Index: 1135073 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1176903 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.1190. Min Act: -0.0001

Data Index: 374241 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 2.1202. Min Range: -2.1202

Max Act: 1.0277. Min Act: -0.0001

Data Index: 468422 (C4 (Web Text))

Max Activating Token Index: 271