Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2294 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.7306. Min Act: -0.0001

Data Index: 913323 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6637. Min Act: -0.0001

Data Index: 1092513 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6653. Min Act: -0.0001

Data Index: 777673 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6025. Min Act: -0.0001

Data Index: 226585 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6155. Min Act: -0.0001

Data Index: 129288 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5964. Min Act: -0.0001

Data Index: 228527 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5775. Min Act: -0.0001

Data Index: 123116 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6035. Min Act: -0.0001

Data Index: 341842 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6427. Min Act: -0.0001

Data Index: 94591 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5510. Min Act: -0.0001

Data Index: 617599 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.6050. Min Act: -0.0001

Data Index: 198591 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5405. Min Act: -0.0001

Data Index: 700778 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1187904 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5880. Min Act: -0.0001

Data Index: 1167811 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5387. Min Act: -0.0001

Data Index: 975022 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5457. Min Act: -0.0001

Data Index: 72116 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5394. Min Act: -0.0001

Data Index: 595705 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5378. Min Act: -0.0001

Data Index: 235439 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5245. Min Act: -0.0001

Data Index: 510477 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.7306. Min Range: -0.7306

Max Act: 0.5087. Min Act: -0.0001

Data Index: 989306 (C4 (Web Text))

Max Activating Token Index: 950