Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2610 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.8388. Min Act: -0.0001

Data Index: 825426 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.7433. Min Act: -0.0001

Data Index: 21726 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.7551. Min Act: -0.0001

Data Index: 1250589 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6819. Min Act: -0.0001

Data Index: 237112 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.7072. Min Act: -0.0001

Data Index: 137764 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6986. Min Act: -0.0001

Data Index: 554219 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.7030. Min Act: -0.0001

Data Index: 1213065 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6737. Min Act: -0.0001

Data Index: 5446 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6413. Min Act: -0.0001

Data Index: 323583 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6232. Min Act: -0.0001

Data Index: 429483 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6204. Min Act: -0.0001

Data Index: 1007110 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6026. Min Act: -0.0001

Data Index: 1114791 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.5941. Min Act: -0.0001

Data Index: 730165 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6051. Min Act: -0.0001

Data Index: 1019567 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6107. Min Act: -0.0001

Data Index: 1013532 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.5948. Min Act: -0.0001

Data Index: 1247667 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6088. Min Act: -0.0001

Data Index: 918143 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6083. Min Act: -0.0001

Data Index: 297981 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6050. Min Act: -0.0001

Data Index: 261534 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.8388. Min Range: -0.8388

Max Act: 0.6038. Min Act: -0.0001

Data Index: 131211 (C4 (Web Text))

Max Activating Token Index: 707