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

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

Neuron 2974 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.6151. Min Act: -0.0000

Data Index: 839484 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.7293. Min Act: -0.0000

Data Index: 1520794 (Python Code)

Max Activating Token Index: 482

Text #2

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.5178. Min Act: -0.0000

Data Index: 874588 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2849. Min Act: -0.0000

Data Index: 671236 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4441. Min Act: -0.0000

Data Index: 245377 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1407452 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1531155 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1338512 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1285146 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2842. Min Act: -0.0000

Data Index: 1458788 (Python Code)

Max Activating Token Index: 717

Text #10

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2884. Min Act: -0.0000

Data Index: 861403 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1071895 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1081227 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1622762 (Python Code)

Max Activating Token Index: 203

Text #14

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.0993. Min Act: -0.0000

Data Index: 1553412 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.1949. Min Act: -0.0000

Data Index: 1316766 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1376482 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.1520. Min Act: -0.0000

Data Index: 210321 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.2469. Min Act: -0.0000

Data Index: 707525 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1072206 (C4 (Web Text))

Max Activating Token Index: 605