Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4431 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.7716. Min Act: -0.0000

Data Index: 1091513 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.7740. Min Act: -0.0000

Data Index: 984093 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.5953. Min Act: -0.0000

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.6065. Min Act: -0.0000

Data Index: 483335 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4081. Min Act: -0.0000

Data Index: 685398 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4566. Min Act: -0.0000

Data Index: 67352 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4521. Min Act: -0.0000

Data Index: 771995 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4436. Min Act: -0.0000

Data Index: 978958 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1087984 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.3578. Min Act: -0.0000

Data Index: 939847 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4296. Min Act: -0.0000

Data Index: 1153985 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4073. Min Act: -0.0000

Data Index: 473664 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.3109. Min Act: -0.0000

Data Index: 833752 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4695. Min Act: -0.0000

Data Index: 751510 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.2953. Min Act: -0.0000

Data Index: 274841 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.3654. Min Act: -0.0000

Data Index: 369341 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.3639. Min Act: -0.0000

Data Index: 1246442 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.4476. Min Act: -0.0000

Data Index: 1161673 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.2538. Min Act: -0.0000

Data Index: 829910 (C4 (Web Text))

Max Activating Token Index: 280