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

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

Neuron 4078 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7925. Min Act: -0.0000

Data Index: 869967 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.7102. Min Act: -0.0000

Data Index: 909575 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1002842 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1102645 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.6202. Min Act: -0.0000

Data Index: 852486 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5854. Min Act: -0.0000

Data Index: 512265 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1256154 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5592. Min Act: -0.0000

Data Index: 423331 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5244. Min Act: -0.0000

Data Index: 529095 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1197527 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5314. Min Act: -0.0000

Data Index: 594673 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5195. Min Act: -0.0000

Data Index: 374165 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5253. Min Act: -0.0000

Data Index: 221747 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5328. Min Act: -0.0000

Data Index: 980301 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.5582. Min Act: -0.0000

Data Index: 557979 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.4695. Min Act: -0.0000

Data Index: 124452 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.4759. Min Act: -0.0000

Data Index: 790273 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1157548 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1058200 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.7925. Min Range: -0.7925

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1300960 (C4 (Web Text))

Max Activating Token Index: 737