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

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

Neuron 2036 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.8357. Min Act: -0.0001

Data Index: 198866 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.7399. Min Act: -0.0001

Data Index: 619349 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.6071. Min Act: -0.0001

Data Index: 441814 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.6334. Min Act: -0.0001

Data Index: 533391 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.5357. Min Act: -0.0001

Data Index: 395438 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1145220 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.3537. Min Act: -0.0001

Data Index: 1037128 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.4085. Min Act: -0.0001

Data Index: 1126439 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2319. Min Act: -0.0001

Data Index: 723748 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.3002. Min Act: -0.0000

Data Index: 144004 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2724. Min Act: -0.0001

Data Index: 664 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.4073. Min Act: -0.0001

Data Index: 1231006 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2064. Min Act: -0.0001

Data Index: 207265 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2578. Min Act: -0.0001

Data Index: 382358 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2854. Min Act: -0.0001

Data Index: 62348 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2483. Min Act: -0.0001

Data Index: 757752 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2844. Min Act: -0.0001

Data Index: 286049 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.3194. Min Act: -0.0001

Data Index: 1036957 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.1981. Min Act: -0.0001

Data Index: 947523 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.8357. Min Range: -1.8357

Max Act: 1.2299. Min Act: -0.0001

Data Index: 758426 (C4 (Web Text))

Max Activating Token Index: 739