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

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

Neuron 4726 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2943. Min Range: -2.2943

Max Act: 2.2943. Min Act: -0.0000

Data Index: 861430 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 2.2943. Min Range: -2.2943

Max Act: 2.1874. Min Act: -0.0000

Data Index: 836598 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 2.2943. Min Range: -2.2943

Max Act: 2.2619. Min Act: -0.0000

Data Index: 335050 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 2.2943. Min Range: -2.2943

Max Act: 2.1557. Min Act: -0.0000

Data Index: 1235324 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 2.2943. Min Range: -2.2943

Max Act: 2.2395. Min Act: -0.0000

Data Index: 603745 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.9921. Min Act: 0.0001

Data Index: 753521 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.8858. Min Act: -0.0000

Data Index: 548355 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.8517. Min Act: 0.0003

Data Index: 433305 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 2.2943. Min Range: -2.2943

Max Act: 2.0896. Min Act: -0.0000

Data Index: 219675 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.7431. Min Act: -0.0000

Data Index: 312538 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.9291. Min Act: -0.0000

Data Index: 438522 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 2.2943. Min Range: -2.2943

Max Act: 2.1269. Min Act: -0.0000

Data Index: 298919 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.7563. Min Act: -0.0000

Data Index: 714423 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.7442. Min Act: 0.0001

Data Index: 290427 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.8277. Min Act: 0.0001

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.8093. Min Act: -0.0000

Data Index: 1198172 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.7738. Min Act: 0.0001

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.7568. Min Act: -0.0000

Data Index: 1089237 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.8417. Min Act: -0.0000

Data Index: 1059502 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.2943. Min Range: -2.2943

Max Act: 1.7270. Min Act: 0.0002

Data Index: 490245 (C4 (Web Text))

Max Activating Token Index: 828