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

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

Neuron 2920 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: 1.4757. Min Range: -1.4757

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1327 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2887. Min Act: -0.0001

Data Index: 294030 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1249032 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.1862. Min Act: -0.0001

Data Index: 737710 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.0183. Min Act: -0.0001

Data Index: 1008345 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.0290. Min Act: -0.0001

Data Index: 762812 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.4757. Min Range: -1.4757

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1223509 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1113587 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9709. Min Act: -0.0001

Data Index: 187899 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9279. Min Act: -0.0001

Data Index: 1288342 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.8921. Min Act: -0.0001

Data Index: 123305 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9366. Min Act: -0.0000

Data Index: 432201 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9544. Min Act: -0.0001

Data Index: 413479 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9771. Min Act: -0.0001

Data Index: 44816 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.8942. Min Act: -0.0000

Data Index: 385356 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9014. Min Act: -0.0001

Data Index: 8939 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.8546. Min Act: -0.0001

Data Index: 137619 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.8943. Min Act: -0.0001

Data Index: 414500 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1334720 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 1.4757. Min Range: -1.4757

Max Act: 0.9725. Min Act: -0.0001

Data Index: 904423 (C4 (Web Text))

Max Activating Token Index: 845