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

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

Neuron 69 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.9333. Min Act: -0.0001

Data Index: 224921 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.7737. Min Act: -0.0001

Data Index: 358426 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.8229. Min Act: -0.0001

Data Index: 39831 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6997. Min Act: -0.0001

Data Index: 445605 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.8061. Min Act: -0.0001

Data Index: 916368 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.7894. Min Act: -0.0001

Data Index: 87636 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.8745. Min Act: -0.0001

Data Index: 947769 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.7175. Min Act: -0.0001

Data Index: 197723 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6264. Min Act: -0.0001

Data Index: 429155 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.8562. Min Act: -0.0001

Data Index: 161543 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6112. Min Act: -0.0001

Data Index: 333996 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.5586. Min Act: -0.0001

Data Index: 125975 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6770. Min Act: -0.0001

Data Index: 543607 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6064. Min Act: -0.0001

Data Index: 1199905 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.5562. Min Act: -0.0001

Data Index: 1119226 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6205. Min Act: -0.0001

Data Index: 1286999 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6640. Min Act: -0.0001

Data Index: 561655 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.5282. Min Act: -0.0001

Data Index: 1306254 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6575. Min Act: -0.0001

Data Index: 482880 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.9333. Min Range: -1.9333

Max Act: 1.6033. Min Act: -0.0001

Data Index: 188020 (C4 (Web Text))

Max Activating Token Index: 626