Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3504 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6246. Min Act: -0.0000

Data Index: 103858 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4968. Min Act: -0.0000

Data Index: 483928 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4903. Min Act: -0.0000

Data Index: 308233 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4874. Min Act: -0.0000

Data Index: 547794 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4572. Min Act: -0.0001

Data Index: 95774 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1097870 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1887 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4356. Min Act: -0.0000

Data Index: 323246 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4270. Min Act: -0.0001

Data Index: 264439 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1007144 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4211. Min Act: -0.0001

Data Index: 1076562 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4213. Min Act: -0.0001

Data Index: 1025407 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4297. Min Act: -0.0000

Data Index: 332255 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1285356 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4195. Min Act: -0.0000

Data Index: 437825 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3680. Min Act: -0.0001

Data Index: 168498 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3941. Min Act: -0.0000

Data Index: 811340 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1258730 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3852. Min Act: -0.0001

Data Index: 1115704 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3845. Min Act: -0.0000

Data Index: 824916 (C4 (Web Text))

Max Activating Token Index: 889