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

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

Neuron 3286 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: 0.3692. Min Range: -0.3692

Max Act: 0.3692. Min Act: -0.0001

Data Index: 235177 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1303688 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3063. Min Act: -0.0001

Data Index: 429667 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3018. Min Act: -0.0001

Data Index: 530706 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2803. Min Act: -0.0001

Data Index: 27161 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2845. Min Act: -0.0000

Data Index: 395917 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1329875 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2815. Min Act: -0.0000

Data Index: 446341 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2662. Min Act: -0.0001

Data Index: 604570 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2560. Min Act: -0.0001

Data Index: 977954 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2444. Min Act: -0.0000

Data Index: 706777 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2612. Min Act: -0.0000

Data Index: 984862 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1327409 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2442. Min Act: -0.0001

Data Index: 633153 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2561. Min Act: -0.0000

Data Index: 554269 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1083304 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2443. Min Act: -0.0000

Data Index: 255318 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2588. Min Act: -0.0000

Data Index: 938707 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2408. Min Act: -0.0001

Data Index: 71670 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1101634 (C4 (Web Text))

Max Activating Token Index: 739