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

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

Neuron 4038 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.7363. Min Act: -0.0001

Data Index: 1103701 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.7205. Min Act: -0.0001

Data Index: 930255 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.7315. Min Act: -0.0001

Data Index: 350972 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6788. Min Act: -0.0001

Data Index: 291196 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6813. Min Act: -0.0001

Data Index: 841494 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6813. Min Act: -0.0001

Data Index: 1280340 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6813. Min Act: -0.0001

Data Index: 165579 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6813. Min Act: -0.0001

Data Index: 151223 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6615. Min Act: -0.0001

Data Index: 813783 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6432. Min Act: -0.0001

Data Index: 1315372 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.7022. Min Act: -0.0001

Data Index: 910371 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6967. Min Act: -0.0001

Data Index: 487219 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6585. Min Act: -0.0001

Data Index: 449217 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6469. Min Act: -0.0001

Data Index: 888540 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6439. Min Act: -0.0001

Data Index: 902167 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6703. Min Act: -0.0001

Data Index: 648102 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6700. Min Act: -0.0001

Data Index: 1017773 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6137. Min Act: -0.0001

Data Index: 1024691 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6631. Min Act: -0.0001

Data Index: 222342 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.7363. Min Range: -0.7363

Max Act: 0.6401. Min Act: -0.0001

Data Index: 196674 (C4 (Web Text))

Max Activating Token Index: 262