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

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

Neuron 1294 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: 1.9324. Min Range: -1.9324

Max Act: 1.9324. Min Act: -0.0001

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.9324. Min Range: -1.9324

Max Act: 1.7791. Min Act: -0.0001

Data Index: 351864 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 1.9324. Min Range: -1.9324

Max Act: 1.4560. Min Act: -0.0001

Data Index: 1282089 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 1.9324. Min Range: -1.9324

Max Act: 1.6081. Min Act: -0.0001

Data Index: 420452 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 1.9324. Min Range: -1.9324

Max Act: 1.1934. Min Act: -0.0001

Data Index: 1250432 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.9324. Min Range: -1.9324

Max Act: 1.0710. Min Act: -0.0001

Data Index: 828842 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.9419. Min Act: -0.0001

Data Index: 1218316 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.9909. Min Act: -0.0001

Data Index: 1298870 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.9192. Min Act: -0.0001

Data Index: 205611 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.9534. Min Act: -0.0001

Data Index: 1047460 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.8911. Min Act: -0.0001

Data Index: 544316 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.8469. Min Act: -0.0001

Data Index: 551542 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.8373. Min Act: -0.0001

Data Index: 1561678 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.8715. Min Act: -0.0001

Data Index: 44701 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.8109. Min Act: -0.0001

Data Index: 345983 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.7856. Min Act: -0.0001

Data Index: 784136 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.8093. Min Act: -0.0001

Data Index: 210737 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.8058. Min Act: -0.0001

Data Index: 223925 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.7377. Min Act: -0.0001

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.9324. Min Range: -1.9324

Max Act: 0.7816. Min Act: -0.0001

Data Index: 99090 (C4 (Web Text))

Max Activating Token Index: 431