Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 655 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.7460. Min Act: -0.0001

Data Index: 1324255 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6974. Min Act: -0.0001

Data Index: 232666 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6154. Min Act: -0.0001

Data Index: 1076215 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5969. Min Act: -0.0001

Data Index: 412980 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6326. Min Act: -0.0001

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6380. Min Act: -0.0001

Data Index: 586311 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5911. Min Act: -0.0001

Data Index: 256107 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6301. Min Act: -0.0001

Data Index: 661835 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6578. Min Act: -0.0001

Data Index: 39663 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6446. Min Act: -0.0001

Data Index: 423261 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5892. Min Act: -0.0001

Data Index: 353285 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5765. Min Act: -0.0001

Data Index: 306957 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5760. Min Act: -0.0001

Data Index: 1128316 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6026. Min Act: -0.0001

Data Index: 191634 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5900. Min Act: -0.0001

Data Index: 166388 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6122. Min Act: -0.0001

Data Index: 310397 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6268. Min Act: -0.0001

Data Index: 170925 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5887. Min Act: -0.0001

Data Index: 1160126 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6233. Min Act: -0.0001

Data Index: 707882 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5655. Min Act: -0.0001

Data Index: 810506 (C4 (Web Text))

Max Activating Token Index: 858