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

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

Neuron 2769 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1176860 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4951. Min Act: -0.0001

Data Index: 192791 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4360. Min Act: -0.0001

Data Index: 642463 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4658. Min Act: -0.0001

Data Index: 996930 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4745. Min Act: -0.0001

Data Index: 871601 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4414. Min Act: -0.0001

Data Index: 216726 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4456. Min Act: -0.0001

Data Index: 1165486 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4348. Min Act: -0.0001

Data Index: 668369 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4459. Min Act: -0.0001

Data Index: 498332 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4553. Min Act: -0.0001

Data Index: 11344 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4371. Min Act: -0.0001

Data Index: 143197 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1356226 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4928. Min Act: -0.0001

Data Index: 714502 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4466. Min Act: -0.0001

Data Index: 748018 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4022. Min Act: -0.0001

Data Index: 1267871 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4003. Min Act: -0.0001

Data Index: 1071013 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3837. Min Act: -0.0001

Data Index: 71676 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4392. Min Act: -0.0001

Data Index: 51578 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4232. Min Act: -0.0001

Data Index: 1227860 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4050. Min Act: -0.0001

Data Index: 670761 (C4 (Web Text))

Max Activating Token Index: 746