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

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

Neuron 258 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.8438. Min Act: -0.0000

Data Index: 941270 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1120366 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.7093. Min Act: -0.0000

Data Index: 493689 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1310018 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5771. Min Act: -0.0000

Data Index: 783713 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1089368 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5988. Min Act: -0.0000

Data Index: 881360 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1087051 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5522. Min Act: -0.0000

Data Index: 385899 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5333. Min Act: -0.0000

Data Index: 962572 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1154894 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5630. Min Act: -0.0000

Data Index: 250995 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5274. Min Act: -0.0000

Data Index: 914778 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1041247 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.5030. Min Act: -0.0000

Data Index: 332950 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1336293 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.4879. Min Act: -0.0000

Data Index: 367745 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.4815. Min Act: -0.0000

Data Index: 993369 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.4531. Min Act: -0.0000

Data Index: 678555 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.8438. Min Range: -0.8438

Max Act: 0.4400. Min Act: -0.0000

Data Index: 134577 (C4 (Web Text))

Max Activating Token Index: 508