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

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

Neuron 4396 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: 3.6901. Min Range: -3.6901

Max Act: 3.6901. Min Act: -0.0000

Data Index: 649995 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 3.6901. Min Range: -3.6901

Max Act: 3.3344. Min Act: -0.0000

Data Index: 517758 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 3.6901. Min Range: -3.6901

Max Act: 2.7174. Min Act: -0.0000

Data Index: 1050784 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.6901. Min Range: -3.6901

Max Act: 2.3628. Min Act: -0.0000

Data Index: 1352485 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 3.6901. Min Range: -3.6901

Max Act: 2.1420. Min Act: -0.0000

Data Index: 1087476 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.8836. Min Act: -0.0000

Data Index: 864299 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.6901. Min Range: -3.6901

Max Act: 2.0629. Min Act: -0.0000

Data Index: 668911 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 3.6901. Min Range: -3.6901

Max Act: 2.0442. Min Act: -0.0001

Data Index: 880330 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.9355. Min Act: -0.0000

Data Index: 62559 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.7203. Min Act: -0.0001

Data Index: 661705 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.8038. Min Act: -0.0000

Data Index: 1119480 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.5987. Min Act: -0.0000

Data Index: 40281 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.8757. Min Act: -0.0001

Data Index: 751490 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.6387. Min Act: -0.0001

Data Index: 125976 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.6550. Min Act: -0.0000

Data Index: 950637 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.4050. Min Act: -0.0000

Data Index: 1451081 (Python Code)

Max Activating Token Index: 190

Text #16

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.6572. Min Act: -0.0000

Data Index: 1176058 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.6299. Min Act: -0.0000

Data Index: 1198824 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.8226. Min Act: -0.0000

Data Index: 4071 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 3.6901. Min Range: -3.6901

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1302757 (C4 (Web Text))

Max Activating Token Index: 243