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

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

Neuron 314 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.3086. Min Act: -0.0001

Data Index: 830076 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2831. Min Act: -0.0001

Data Index: 1186564 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2467. Min Act: -0.0001

Data Index: 1017714 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2472. Min Act: -0.0001

Data Index: 932592 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2648. Min Act: -0.0001

Data Index: 900556 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2368. Min Act: -0.0001

Data Index: 266924 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2861. Min Act: -0.0001

Data Index: 1102152 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1150070 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2329. Min Act: -0.0001

Data Index: 507394 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1146576 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2095. Min Act: -0.0001

Data Index: 314145 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2450. Min Act: -0.0001

Data Index: 540020 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2110. Min Act: -0.0001

Data Index: 527974 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2299. Min Act: -0.0001

Data Index: 379755 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2199. Min Act: -0.0001

Data Index: 934625 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2185. Min Act: -0.0001

Data Index: 893972 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2126. Min Act: -0.0001

Data Index: 172184 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2392. Min Act: -0.0001

Data Index: 347118 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2293. Min Act: -0.0001

Data Index: 431326 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1741. Min Act: -0.0001

Data Index: 426519 (C4 (Web Text))

Max Activating Token Index: 244