Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4120 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.8302. Min Act: -0.0000

Data Index: 335269 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.5577. Min Act: -0.0000

Data Index: 1001154 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.4346. Min Act: -0.0000

Data Index: 301126 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.3697. Min Act: -0.0000

Data Index: 335352 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.4363. Min Act: -0.0000

Data Index: 1060774 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.5192. Min Act: -0.0000

Data Index: 238648 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.8230. Min Act: -0.0000

Data Index: 1021280 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.8932. Min Act: -0.0000

Data Index: 586160 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.7288. Min Act: -0.0000

Data Index: 854745 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.9453. Min Act: -0.0000

Data Index: 14184 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.9168. Min Act: -0.0000

Data Index: 755201 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.7920. Min Act: -0.0000

Data Index: 244147 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.8885. Min Act: -0.0000

Data Index: 13577 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.8831. Min Act: -0.0000

Data Index: 526865 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.7355. Min Act: -0.0000

Data Index: 764394 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.5686. Min Act: -0.0000

Data Index: 1162774 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.8608. Min Act: -0.0000

Data Index: 889467 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.8411. Min Act: -0.0000

Data Index: 1175798 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.6194. Min Act: -0.0000

Data Index: 686243 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 3.8302. Min Range: -3.8302

Max Act: 2.7023. Min Act: -0.0000

Data Index: 1217565 (C4 (Web Text))

Max Activating Token Index: 269