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

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

Neuron 4490 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: 0.3407. Min Range: -0.3407

Max Act: 0.3407. Min Act: -0.0000

Data Index: 434647 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1218538 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.0652. Min Act: -0.0001

Data Index: 108459 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1470. Min Act: -0.0000

Data Index: 955474 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1011. Min Act: -0.0000

Data Index: 796665 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1339177 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1077. Min Act: -0.0000

Data Index: 731670 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1355207 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1149. Min Act: -0.0001

Data Index: 94172 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1178. Min Act: -0.0000

Data Index: 176190 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1085. Min Act: -0.0001

Data Index: 477840 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1138. Min Act: -0.0001

Data Index: 797180 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1247. Min Act: -0.0000

Data Index: 408328 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.0962. Min Act: -0.0000

Data Index: 859238 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1175. Min Act: -0.0000

Data Index: 75767 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1180. Min Act: -0.0001

Data Index: 341791 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1139. Min Act: -0.0000

Data Index: 250866 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1344276 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.0990. Min Act: -0.0000

Data Index: 165784 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.3407. Min Range: -0.3407

Max Act: 0.1064. Min Act: -0.0000

Data Index: 111313 (C4 (Web Text))

Max Activating Token Index: 998