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

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

Neuron 5870 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2496. Min Act: -0.0000

Data Index: 312711 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2359. Min Act: -0.0000

Data Index: 480254 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2233. Min Act: -0.0000

Data Index: 660781 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2427. Min Act: -0.0001

Data Index: 482463 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2073. Min Act: -0.0000

Data Index: 370104 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1207219 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2362. Min Act: -0.0000

Data Index: 697959 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2374. Min Act: -0.0000

Data Index: 753050 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1232738 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2530. Min Act: -0.0000

Data Index: 659898 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2196. Min Act: -0.0000

Data Index: 607443 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1120400 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2164. Min Act: -0.0000

Data Index: 854517 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2300. Min Act: -0.0001

Data Index: 445118 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2176. Min Act: -0.0000

Data Index: 3413 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2105. Min Act: -0.0000

Data Index: 387290 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1125534 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1728. Min Act: -0.0000

Data Index: 805593 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2128. Min Act: -0.0001

Data Index: 532107 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1107298 (C4 (Web Text))

Max Activating Token Index: 134