Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5035 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.5599. Min Act: -0.0000

Data Index: 1091467 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.5450. Min Act: -0.0000

Data Index: 626758 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.5920. Min Act: -0.0000

Data Index: 643422 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4908. Min Act: -0.0000

Data Index: 1067975 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1085153 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3965. Min Act: -0.0000

Data Index: 307318 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3791. Min Act: -0.0000

Data Index: 815738 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4336. Min Act: -0.0000

Data Index: 626438 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4906. Min Act: -0.0000

Data Index: 915337 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3467. Min Act: -0.0000

Data Index: 1237773 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1171762 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3781. Min Act: -0.0000

Data Index: 1336981 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3515. Min Act: -0.0000

Data Index: 164775 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3323. Min Act: -0.0000

Data Index: 821003 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3388. Min Act: -0.0000

Data Index: 349930 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1011565 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3173. Min Act: -0.0000

Data Index: 388793 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3152. Min Act: -0.0000

Data Index: 1282189 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1568592 (Python Code)

Max Activating Token Index: 116

Text #19

Max Range: 1.5920. Min Range: -1.5920

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1098670 (C4 (Web Text))

Max Activating Token Index: 324