Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1738 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0006

Data Index: 1098574 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0330. Min Act: -0.0006

Data Index: 937879 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0318. Min Act: -0.0006

Data Index: 477276 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1031318 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0300. Min Act: -0.0006

Data Index: 601966 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0315. Min Act: -0.0006

Data Index: 94605 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0311. Min Act: -0.0006

Data Index: 967771 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0309. Min Act: -0.0006

Data Index: 705715 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0305. Min Act: -0.0006

Data Index: 635134 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0295. Min Act: -0.0006

Data Index: 852563 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0299. Min Act: -0.0006

Data Index: 809633 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1588740 (Python Code)

Max Activating Token Index: 965

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0297. Min Act: -0.0006

Data Index: 118005 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1129120 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0283. Min Act: -0.0006

Data Index: 421965 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0287. Min Act: -0.0006

Data Index: 52138 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0282. Min Act: -0.0006

Data Index: 146455 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0281. Min Act: -0.0006

Data Index: 23536 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1282085 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0282. Min Act: -0.0006

Data Index: 1152670 (C4 (Web Text))

Max Activating Token Index: 297