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

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

Neuron 1602 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: 3.2293. Min Range: -3.2293

Max Act: 3.2293. Min Act: -0.0000

Data Index: 444378 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 3.2293. Min Range: -3.2293

Max Act: 3.0394. Min Act: -0.0000

Data Index: 579761 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8831. Min Act: -0.0000

Data Index: 295454 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.9891. Min Act: -0.0000

Data Index: 253954 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.7169. Min Act: -0.0000

Data Index: 1004072 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.8390. Min Act: -0.0000

Data Index: 853179 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6764. Min Act: -0.0000

Data Index: 1105574 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6510. Min Act: -0.0000

Data Index: 51121 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.6480. Min Act: -0.0000

Data Index: 311847 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.5616. Min Act: -0.0000

Data Index: 1103973 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.3713. Min Act: -0.0000

Data Index: 329441 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.3840. Min Act: -0.0000

Data Index: 797477 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.2609. Min Act: -0.0000

Data Index: 1253214 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.2514. Min Act: -0.0000

Data Index: 628407 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.3709. Min Act: -0.0000

Data Index: 83732 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.2889. Min Act: -0.0000

Data Index: 1038994 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.2839. Min Act: -0.0000

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.2634. Min Act: -0.0000

Data Index: 90052 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.3787. Min Act: -0.0000

Data Index: 177467 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 3.2293. Min Range: -3.2293

Max Act: 2.2513. Min Act: -0.0000

Data Index: 412173 (C4 (Web Text))

Max Activating Token Index: 171