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

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

Neuron 1201 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4337. Min Act: -0.0003

Data Index: 313615 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4302. Min Act: -0.0003

Data Index: 316289 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4116. Min Act: -0.0003

Data Index: 1200010 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4191. Min Act: -0.0003

Data Index: 974549 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3636. Min Act: -0.0003

Data Index: 947681 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4026. Min Act: -0.0003

Data Index: 668039 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3894. Min Act: -0.0003

Data Index: 1062114 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3982. Min Act: -0.0003

Data Index: 440323 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3584. Min Act: -0.0003

Data Index: 230898 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3807. Min Act: -0.0003

Data Index: 432284 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3851. Min Act: -0.0003

Data Index: 1028663 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3897. Min Act: -0.0003

Data Index: 1330532 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3860. Min Act: -0.0003

Data Index: 779097 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3991. Min Act: -0.0003

Data Index: 949468 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3732. Min Act: -0.0003

Data Index: 686483 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3723. Min Act: -0.0003

Data Index: 1085761 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3844. Min Act: -0.0003

Data Index: 294848 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3692. Min Act: -0.0003

Data Index: 1204528 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3936. Min Act: -0.0003

Data Index: 804067 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3792. Min Act: -0.0003

Data Index: 503397 (C4 (Web Text))

Max Activating Token Index: 700