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

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

Neuron 433 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.5160. Min Act: -0.0002

Data Index: 1055877 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3561. Min Act: -0.0002

Data Index: 868424 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2769. Min Act: -0.0001

Data Index: 974350 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.4320. Min Act: -0.0002

Data Index: 942227 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.3082. Min Act: -0.0001

Data Index: 298376 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2241. Min Act: -0.0001

Data Index: 785286 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2221. Min Act: -0.0002

Data Index: 850456 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.1819. Min Act: -0.0001

Data Index: 14431 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.2508. Min Act: -0.0001

Data Index: 515083 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0365. Min Act: -0.0001

Data Index: 1104717 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.1456. Min Act: -0.0001

Data Index: 1233297 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0976. Min Act: -0.0002

Data Index: 779418 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 1.5160. Min Range: -1.5160

Max Act: 0.9927. Min Act: -0.0002

Data Index: 918729 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0764. Min Act: -0.0001

Data Index: 556967 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.1306. Min Act: -0.0001

Data Index: 964732 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0542. Min Act: -0.0002

Data Index: 526103 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0513. Min Act: -0.0001

Data Index: 861130 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0331. Min Act: -0.0002

Data Index: 934881 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0416. Min Act: -0.0001

Data Index: 1246217 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 1.5160. Min Range: -1.5160

Max Act: 1.0058. Min Act: -0.0002

Data Index: 566638 (C4 (Web Text))

Max Activating Token Index: 595