Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 562 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.6238. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.4510. Min Act: -0.0003

Data Index: 1643548 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.2334. Min Act: -0.0003

Data Index: 1409000 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.2057. Min Act: -0.0003

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.1429. Min Act: -0.0003

Data Index: 1421588 (Python Code)

Max Activating Token Index: 818

Text #5

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.1202. Min Act: -0.0003

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0793. Min Act: -0.0003

Data Index: 1467808 (Python Code)

Max Activating Token Index: 943

Text #7

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0780. Min Act: -0.0003

Data Index: 1497881 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0672. Min Act: -0.0003

Data Index: 162160 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0642. Min Act: -0.0003

Data Index: 451109 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1178222 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0629. Min Act: -0.0003

Data Index: 43832 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1325669 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0544. Min Act: -0.0003

Data Index: 198747 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0570. Min Act: -0.0003

Data Index: 162255 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0565. Min Act: -0.0003

Data Index: 977926 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0536. Min Act: -0.0003

Data Index: 503632 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0525. Min Act: -0.0003

Data Index: 416778 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0513. Min Act: -0.0003

Data Index: 138542 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.6238. Min Range: -0.6238

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1338354 (C4 (Web Text))

Max Activating Token Index: 123