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

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

Neuron 2295 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7800. Min Act: -0.0003

Data Index: 163921 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7674. Min Act: -0.0003

Data Index: 1500115 (Python Code)

Max Activating Token Index: 346

Text #2

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8240. Min Act: -0.0003

Data Index: 982251 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7297. Min Act: -0.0003

Data Index: 811176 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7494. Min Act: -0.0003

Data Index: 930549 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6889. Min Act: -0.0003

Data Index: 955984 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7192. Min Act: -0.0003

Data Index: 610965 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6752. Min Act: -0.0003

Data Index: 131250 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7909. Min Act: -0.0003

Data Index: 453234 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6484. Min Act: -0.0003

Data Index: 509086 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6614. Min Act: -0.0003

Data Index: 1169990 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6560. Min Act: -0.0003

Data Index: 1262041 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6990. Min Act: -0.0003

Data Index: 536499 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6535. Min Act: -0.0003

Data Index: 468962 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5992. Min Act: -0.0003

Data Index: 348302 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6778. Min Act: -0.0003

Data Index: 1435660 (Python Code)

Max Activating Token Index: 881

Text #16

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6704. Min Act: -0.0003

Data Index: 1320476 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.5852. Min Act: -0.0003

Data Index: 1202424 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6041. Min Act: -0.0003

Data Index: 392390 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6244. Min Act: -0.0003

Data Index: 583299 (C4 (Web Text))

Max Activating Token Index: 75