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

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

Neuron 2418 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: 1.1314. Min Range: -1.1314

Max Act: 1.1314. Min Act: -0.0001

Data Index: 1162124 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9609. Min Act: -0.0001

Data Index: 98926 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.9708. Min Act: -0.0001

Data Index: 419822 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8798. Min Act: -0.0001

Data Index: 911200 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8671. Min Act: -0.0001

Data Index: 311497 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8567. Min Act: -0.0001

Data Index: 1108197 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8894. Min Act: -0.0001

Data Index: 650744 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8899. Min Act: -0.0001

Data Index: 211805 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8728. Min Act: -0.0001

Data Index: 890153 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8097. Min Act: -0.0001

Data Index: 225290 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8357. Min Act: -0.0001

Data Index: 257360 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.7706. Min Act: -0.0001

Data Index: 1168198 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.7839. Min Act: -0.0001

Data Index: 135041 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8104. Min Act: -0.0001

Data Index: 836918 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8748. Min Act: -0.0001

Data Index: 361168 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1194280 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8292. Min Act: -0.0001

Data Index: 296822 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8382. Min Act: -0.0001

Data Index: 991108 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8017. Min Act: -0.0001

Data Index: 39859 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 1.1314. Min Range: -1.1314

Max Act: 0.8296. Min Act: -0.0001

Data Index: 221933 (C4 (Web Text))

Max Activating Token Index: 644