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

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

Neuron 935 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.9890. Min Act: -0.0000

Data Index: 561484 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.7540. Min Act: -0.0000

Data Index: 582632 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.8941. Min Act: -0.0000

Data Index: 1019138 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.7326. Min Act: -0.0000

Data Index: 384331 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.9444. Min Act: -0.0000

Data Index: 1146518 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.7571. Min Act: -0.0000

Data Index: 501645 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.6019. Min Act: -0.0000

Data Index: 733539 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.8678. Min Act: -0.0000

Data Index: 340148 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.7253. Min Act: -0.0000

Data Index: 673878 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5855. Min Act: -0.0000

Data Index: 449064 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5549. Min Act: -0.0000

Data Index: 1263587 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5461. Min Act: -0.0000

Data Index: 1353219 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.7620. Min Act: -0.0000

Data Index: 37382 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5669. Min Act: -0.0000

Data Index: 29591 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5301. Min Act: -0.0000

Data Index: 104681 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5352. Min Act: -0.0000

Data Index: 690446 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5312. Min Act: -0.0000

Data Index: 21725 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.4073. Min Act: -0.0000

Data Index: 646062 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5040. Min Act: -0.0000

Data Index: 921613 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 2.9890. Min Range: -2.9890

Max Act: 2.5075. Min Act: -0.0000

Data Index: 1266963 (C4 (Web Text))

Max Activating Token Index: 437