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

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

Neuron 3437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2800. Min Range: -2.2800

Max Act: 2.2800. Min Act: -0.0000

Data Index: 978114 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 2.2800. Min Range: -2.2800

Max Act: 2.1661. Min Act: -0.0000

Data Index: 647017 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.9353. Min Act: -0.0000

Data Index: 543812 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.9522. Min Act: -0.0000

Data Index: 1353961 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.7594. Min Act: -0.0000

Data Index: 1240464 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.8523. Min Act: -0.0000

Data Index: 1032114 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1346912 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 2.2800. Min Range: -2.2800

Max Act: 2.0245. Min Act: -0.0000

Data Index: 1198855 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.8445. Min Act: -0.0000

Data Index: 973968 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.7363. Min Act: -0.0001

Data Index: 1317488 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.7419. Min Act: -0.0000

Data Index: 1348123 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.5455. Min Act: -0.0000

Data Index: 152904 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.5325. Min Act: -0.0000

Data Index: 843243 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.7182. Min Act: -0.0000

Data Index: 94867 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.5961. Min Act: -0.0000

Data Index: 503946 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.5461. Min Act: -0.0000

Data Index: 195804 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.5322. Min Act: -0.0000

Data Index: 868618 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.3855. Min Act: -0.0000

Data Index: 21053 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.5333. Min Act: -0.0000

Data Index: 903529 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 2.2800. Min Range: -2.2800

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1132684 (C4 (Web Text))

Max Activating Token Index: 513