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

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

Neuron 1471 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.8815. Min Act: -0.0000

Data Index: 538402 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 3.1254. Min Range: -3.1254

Max Act: 3.1254. Min Act: -0.0000

Data Index: 679361 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.7255. Min Act: -0.0000

Data Index: 530390 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.4380. Min Act: -0.0001

Data Index: 269300 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.4570. Min Act: -0.0000

Data Index: 929425 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.1187. Min Act: -0.0000

Data Index: 142914 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.6643. Min Act: -0.0000

Data Index: 963433 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.4451. Min Act: -0.0000

Data Index: 555088 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.3974. Min Act: -0.0000

Data Index: 1235764 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.1679. Min Act: -0.0000

Data Index: 28379 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.1732. Min Act: -0.0000

Data Index: 250449 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.3311. Min Act: -0.0000

Data Index: 1348272 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.4618. Min Act: -0.0001

Data Index: 821071 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.3501. Min Act: -0.0000

Data Index: 939832 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.3236. Min Act: -0.0000

Data Index: 1320763 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.2643. Min Act: -0.0000

Data Index: 484301 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.3125. Min Act: -0.0001

Data Index: 807676 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.0890. Min Act: -0.0000

Data Index: 180043 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.0910. Min Act: -0.0000

Data Index: 732227 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.1707. Min Act: -0.0000

Data Index: 159667 (C4 (Web Text))

Max Activating Token Index: 916