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

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

Neuron 644 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.3455. Min Act: -0.0000

Data Index: 330700 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2426. Min Act: -0.0000

Data Index: 817984 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1211588 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2491. Min Act: -0.0000

Data Index: 94778 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2161. Min Act: -0.0001

Data Index: 758154 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1104147 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2181. Min Act: -0.0000

Data Index: 853137 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2156. Min Act: -0.0000

Data Index: 935524 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2255. Min Act: -0.0001

Data Index: 953269 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.1994. Min Act: -0.0000

Data Index: 245139 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2054. Min Act: -0.0001

Data Index: 980662 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2143. Min Act: -0.0000

Data Index: 264177 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2069. Min Act: -0.0001

Data Index: 945649 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.1955. Min Act: -0.0000

Data Index: 943731 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2094. Min Act: -0.0000

Data Index: 711241 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.1991. Min Act: -0.0000

Data Index: 873005 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1035160 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.1879. Min Act: -0.0000

Data Index: 422430 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1071265 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.3455. Min Range: -0.3455

Max Act: 0.1909. Min Act: -0.0000

Data Index: 945521 (C4 (Web Text))

Max Activating Token Index: 704