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

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

Neuron 4648 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: 1.7348. Min Range: -1.7348

Max Act: 1.6047. Min Act: -0.0000

Data Index: 1121664 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.7348. Min Act: -0.0000

Data Index: 838492 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.5268. Min Act: -0.0000

Data Index: 742478 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1347418 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4628. Min Act: -0.0000

Data Index: 1344488 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1020465 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3847. Min Act: -0.0000

Data Index: 941097 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4606. Min Act: -0.0000

Data Index: 993070 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4582. Min Act: -0.0000

Data Index: 780247 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4419. Min Act: -0.0000

Data Index: 995904 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4433. Min Act: -0.0000

Data Index: 1335307 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4390. Min Act: -0.0000

Data Index: 605186 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3509. Min Act: -0.0000

Data Index: 861772 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3303. Min Act: -0.0000

Data Index: 275832 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4889. Min Act: -0.0000

Data Index: 563596 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.4085. Min Act: -0.0000

Data Index: 66413 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.5668. Min Act: -0.0000

Data Index: 255859 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3998. Min Act: -0.0000

Data Index: 126320 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3855. Min Act: -0.0000

Data Index: 636264 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 1.7348. Min Range: -1.7348

Max Act: 1.3818. Min Act: -0.0000

Data Index: 47290 (C4 (Web Text))

Max Activating Token Index: 295