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

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

Neuron 3698 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.9496. Min Act: -0.0001

Data Index: 604604 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.8438. Min Act: -0.0001

Data Index: 515619 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7696. Min Act: -0.0001

Data Index: 54166 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7372. Min Act: -0.0001

Data Index: 359431 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7356. Min Act: -0.0001

Data Index: 344872 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7198. Min Act: -0.0001

Data Index: 665066 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7471. Min Act: -0.0001

Data Index: 499748 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7132. Min Act: -0.0001

Data Index: 357961 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.6757. Min Act: -0.0001

Data Index: 233512 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7110. Min Act: -0.0001

Data Index: 20524 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.7231. Min Act: -0.0001

Data Index: 1218080 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.6428. Min Act: -0.0001

Data Index: 850423 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.6184. Min Act: -0.0001

Data Index: 906350 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.6164. Min Act: -0.0001

Data Index: 1189472 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.6027. Min Act: -0.0001

Data Index: 1215512 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.5975. Min Act: -0.0001

Data Index: 657786 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.6271. Min Act: -0.0001

Data Index: 1247213 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.5989. Min Act: -0.0001

Data Index: 187932 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.5878. Min Act: -0.0001

Data Index: 772735 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.9496. Min Range: -0.9496

Max Act: 0.5038. Min Act: -0.0001

Data Index: 733058 (C4 (Web Text))

Max Activating Token Index: 714