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

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

Neuron 1363 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5652. Min Act: -0.0000

Data Index: 739264 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5382. Min Act: -0.0000

Data Index: 457389 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1177926 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4721. Min Act: -0.0001

Data Index: 582669 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4724. Min Act: -0.0001

Data Index: 906949 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4607. Min Act: -0.0001

Data Index: 771289 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4950. Min Act: -0.0001

Data Index: 333434 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4399. Min Act: -0.0001

Data Index: 665221 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4446. Min Act: -0.0001

Data Index: 21397 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4554. Min Act: -0.0000

Data Index: 772939 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4371. Min Act: -0.0000

Data Index: 70560 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4522. Min Act: -0.0000

Data Index: 585266 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4605. Min Act: -0.0001

Data Index: 965747 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4383. Min Act: -0.0001

Data Index: 284624 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4551. Min Act: -0.0001

Data Index: 459332 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4178. Min Act: -0.0001

Data Index: 276073 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4132. Min Act: -0.0001

Data Index: 606371 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.4133. Min Act: -0.0001

Data Index: 614195 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.3884. Min Act: -0.0001

Data Index: 77700 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.5652. Min Range: -0.5652

Max Act: 0.3934. Min Act: -0.0001

Data Index: 1087931 (C4 (Web Text))

Max Activating Token Index: 308