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

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

Neuron 5292 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.8268. Min Act: -0.0001

Data Index: 898408 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 4.2285. Min Range: -4.2285

Max Act: 4.2285. Min Act: -0.0000

Data Index: 505084 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.9723. Min Act: -0.0000

Data Index: 435089 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.4593. Min Act: -0.0000

Data Index: 526887 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.7052. Min Act: -0.0001

Data Index: 41503 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.3601. Min Act: -0.0001

Data Index: 869337 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.6605. Min Act: -0.0000

Data Index: 1350346 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.4648. Min Act: -0.0000

Data Index: 986670 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.1842. Min Act: -0.0001

Data Index: 324810 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.4442. Min Act: -0.0001

Data Index: 482483 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.6709. Min Act: -0.0001

Data Index: 1285782 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.2923. Min Act: -0.0001

Data Index: 624698 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.3160. Min Act: -0.0000

Data Index: 547595 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.0244. Min Act: -0.0001

Data Index: 1166101 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.0188. Min Act: -0.0001

Data Index: 553530 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 4.2285. Min Range: -4.2285

Max Act: 2.9801. Min Act: -0.0001

Data Index: 443485 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.0934. Min Act: -0.0001

Data Index: 550407 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 4.2285. Min Range: -4.2285

Max Act: 3.0776. Min Act: -0.0001

Data Index: 614562 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 4.2285. Min Range: -4.2285

Max Act: 2.7244. Min Act: -0.0000

Data Index: 269158 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 4.2285. Min Range: -4.2285

Max Act: 2.9677. Min Act: -0.0001

Data Index: 755591 (C4 (Web Text))

Max Activating Token Index: 313