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

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

Neuron 1116 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.5240. Min Act: 0.0000

Data Index: 1314943 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.4392. Min Act: -0.0000

Data Index: 1188889 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.3797. Min Act: 0.0000

Data Index: 987650 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.4600. Min Act: -0.0000

Data Index: 1281827 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.2833. Min Act: -0.0000

Data Index: 320128 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.1819. Min Act: 0.0000

Data Index: 602693 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.1479. Min Act: -0.0000

Data Index: 649873 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.1373. Min Act: 0.0000

Data Index: 634820 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.0666. Min Act: -0.0000

Data Index: 79829 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.0125. Min Act: -0.0000

Data Index: 1173760 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 2.5240. Min Range: -2.5240

Max Act: 2.0269. Min Act: -0.0000

Data Index: 913092 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.9358. Min Act: -0.0000

Data Index: 1129158 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.9557. Min Act: -0.0000

Data Index: 53801 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.7224. Min Act: -0.0000

Data Index: 1270400 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.9138. Min Act: -0.0000

Data Index: 357972 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.7710. Min Act: -0.0000

Data Index: 1137536 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.6470. Min Act: -0.0000

Data Index: 526621 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.7500. Min Act: 0.0001

Data Index: 694905 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.5854. Min Act: -0.0000

Data Index: 591471 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 2.5240. Min Range: -2.5240

Max Act: 1.6628. Min Act: -0.0000

Data Index: 76557 (C4 (Web Text))

Max Activating Token Index: 1014