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

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

Neuron 1268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.7550. Min Act: -0.0001

Data Index: 288277 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.5765. Min Act: -0.0001

Data Index: 918891 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.6624. Min Act: -0.0001

Data Index: 1049833 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.6880. Min Act: -0.0001

Data Index: 378344 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.6375. Min Act: -0.0001

Data Index: 1223721 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.4906. Min Act: -0.0001

Data Index: 1228487 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.5869. Min Act: -0.0001

Data Index: 1224074 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.6241. Min Act: -0.0001

Data Index: 104003 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.5983. Min Act: -0.0001

Data Index: 167671 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.5491. Min Act: -0.0001

Data Index: 99944 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.5832. Min Act: -0.0001

Data Index: 644519 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.6239. Min Act: -0.0001

Data Index: 683175 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.4827. Min Act: -0.0001

Data Index: 882144 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.4942. Min Act: -0.0001

Data Index: 1114452 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.5311. Min Act: -0.0001

Data Index: 196566 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.4987. Min Act: -0.0001

Data Index: 1334614 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.4878. Min Act: -0.0001

Data Index: 551302 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.4349. Min Act: -0.0001

Data Index: 358432 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.3856. Min Act: -0.0001

Data Index: 1324402 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.7550. Min Range: -1.7550

Max Act: 1.3708. Min Act: -0.0001

Data Index: 1313583 (C4 (Web Text))

Max Activating Token Index: 917