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

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

Neuron 3619 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3692. Min Act: -0.0000

Data Index: 209000 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3166. Min Act: -0.0000

Data Index: 834668 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2381. Min Act: -0.0001

Data Index: 1082924 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1246463 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1309193 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3532. Min Act: -0.0000

Data Index: 815866 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1101917 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1206841 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2642. Min Act: -0.0000

Data Index: 517044 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3470. Min Act: -0.0000

Data Index: 372439 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2479. Min Act: -0.0000

Data Index: 1029093 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.3020. Min Act: -0.0000

Data Index: 778022 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2042. Min Act: -0.0000

Data Index: 501194 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2987. Min Act: -0.0000

Data Index: 158695 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2552. Min Act: -0.0000

Data Index: 900284 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2868. Min Act: -0.0000

Data Index: 102701 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2752. Min Act: -0.0000

Data Index: 697911 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2151. Min Act: -0.0000

Data Index: 573879 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1197459 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.3692. Min Range: -1.3692

Max Act: 1.2593. Min Act: -0.0000

Data Index: 460084 (C4 (Web Text))

Max Activating Token Index: 248