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

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

Neuron 3921 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: 1.4848. Min Range: -1.4848

Max Act: 1.4848. Min Act: -0.0001

Data Index: 725118 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.1922. Min Act: -0.0001

Data Index: 286052 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.1129. Min Act: -0.0000

Data Index: 269310 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0380. Min Act: -0.0001

Data Index: 438874 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0468. Min Act: -0.0001

Data Index: 543278 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0776. Min Act: -0.0001

Data Index: 63152 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.4848. Min Range: -1.4848

Max Act: 1.0467. Min Act: -0.0000

Data Index: 1336796 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9759. Min Act: -0.0001

Data Index: 341230 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9831. Min Act: -0.0001

Data Index: 1321662 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.8611. Min Act: -0.0001

Data Index: 917429 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9598. Min Act: -0.0001

Data Index: 1291440 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9723. Min Act: -0.0001

Data Index: 576072 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9246. Min Act: -0.0001

Data Index: 455435 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.8766. Min Act: -0.0001

Data Index: 1204142 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.8692. Min Act: -0.0001

Data Index: 558085 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.9112. Min Act: -0.0001

Data Index: 430732 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.8426. Min Act: -0.0001

Data Index: 882188 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.8141. Min Act: -0.0001

Data Index: 753819 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.8686. Min Act: -0.0001

Data Index: 720260 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.4848. Min Range: -1.4848

Max Act: 0.8369. Min Act: -0.0001

Data Index: 1330624 (C4 (Web Text))

Max Activating Token Index: 518