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

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

Neuron 1004 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.3109. Min Act: -0.0000

Data Index: 203314 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1562941 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1483359 (Python Code)

Max Activating Token Index: 268

Text #3

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1645043 (Python Code)

Max Activating Token Index: 752

Text #4

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2583. Min Act: -0.0000

Data Index: 671771 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1385981 (Python Code)

Max Activating Token Index: 809

Text #6

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1221759 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2535. Min Act: -0.0000

Data Index: 868847 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2277. Min Act: -0.0000

Data Index: 86563 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2403. Min Act: -0.0000

Data Index: 528004 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2315. Min Act: -0.0000

Data Index: 214787 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2131. Min Act: -0.0000

Data Index: 210201 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2230. Min Act: -0.0000

Data Index: 314996 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2238. Min Act: -0.0000

Data Index: 676269 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1432125 (Python Code)

Max Activating Token Index: 970

Text #15

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2223. Min Act: -0.0000

Data Index: 600010 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2144. Min Act: -0.0000

Data Index: 507284 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2348. Min Act: -0.0000

Data Index: 556423 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.1993. Min Act: -0.0000

Data Index: 933150 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.3183. Min Range: -0.3183

Max Act: 0.2141. Min Act: -0.0001

Data Index: 274797 (C4 (Web Text))

Max Activating Token Index: 607