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

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

Neuron 526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3396. Min Range: -2.3396

Max Act: 2.3396. Min Act: -0.0000

Data Index: 1122871 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 2.3396. Min Range: -2.3396

Max Act: 2.1904. Min Act: -0.0000

Data Index: 497029 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 2.3396. Min Range: -2.3396

Max Act: 2.1871. Min Act: -0.0000

Data Index: 846982 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.3396. Min Range: -2.3396

Max Act: 2.1033. Min Act: -0.0000

Data Index: 1131973 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.9701. Min Act: -0.0000

Data Index: 396319 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 2.3396. Min Range: -2.3396

Max Act: 2.0233. Min Act: -0.0001

Data Index: 14292 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.3396. Min Range: -2.3396

Max Act: 2.0746. Min Act: -0.0001

Data Index: 937684 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 2.3396. Min Range: -2.3396

Max Act: 2.0835. Min Act: -0.0000

Data Index: 1339447 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.9681. Min Act: -0.0000

Data Index: 148607 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.9490. Min Act: -0.0000

Data Index: 124309 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.9265. Min Act: -0.0001

Data Index: 91455 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1123472 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.7468. Min Act: -0.0001

Data Index: 1109253 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.8487. Min Act: -0.0001

Data Index: 393642 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.8528. Min Act: -0.0000

Data Index: 1348335 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.8390. Min Act: -0.0000

Data Index: 227907 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.9183. Min Act: -0.0001

Data Index: 648821 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.8052. Min Act: -0.0000

Data Index: 308077 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.7698. Min Act: -0.0001

Data Index: 1275596 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.3396. Min Range: -2.3396

Max Act: 1.7661. Min Act: -0.0000

Data Index: 1055762 (C4 (Web Text))

Max Activating Token Index: 341