Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5260. Min Act: -0.0001

Data Index: 639024 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5140. Min Act: -0.0000

Data Index: 373214 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1332813 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1075099 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4832. Min Act: -0.0000

Data Index: 185244 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1066637 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4706. Min Act: -0.0001

Data Index: 577334 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4556. Min Act: -0.0001

Data Index: 807444 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4395. Min Act: -0.0000

Data Index: 261567 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1124216 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4520. Min Act: -0.0000

Data Index: 238280 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4308. Min Act: -0.0001

Data Index: 1083167 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.3963. Min Act: -0.0000

Data Index: 510115 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4049. Min Act: -0.0001

Data Index: 1042780 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1337327 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.4106. Min Act: -0.0000

Data Index: 620119 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1311467 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.3956. Min Act: -0.0001

Data Index: 1052195 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.3709. Min Act: -0.0000

Data Index: 733015 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.5260. Min Range: -0.5260

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1171545 (C4 (Web Text))

Max Activating Token Index: 633