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

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

Neuron 2797 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: 1.6330. Min Range: -1.6330

Max Act: 1.6330. Min Act: -0.0001

Data Index: 1208896 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5496. Min Act: -0.0001

Data Index: 57462 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5631. Min Act: -0.0001

Data Index: 1338468 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4940. Min Act: -0.0001

Data Index: 1145692 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5281. Min Act: -0.0001

Data Index: 993937 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4208. Min Act: -0.0001

Data Index: 100213 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5737. Min Act: -0.0001

Data Index: 1314306 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5268. Min Act: -0.0001

Data Index: 213805 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.5259. Min Act: -0.0001

Data Index: 1523708 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4672. Min Act: -0.0001

Data Index: 328587 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4099. Min Act: -0.0001

Data Index: 300734 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4518. Min Act: -0.0001

Data Index: 419859 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4031. Min Act: -0.0001

Data Index: 380099 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4365. Min Act: -0.0001

Data Index: 1464758 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4777. Min Act: -0.0001

Data Index: 927512 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4337. Min Act: -0.0001

Data Index: 958088 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4254. Min Act: -0.0001

Data Index: 1297756 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.3663. Min Act: -0.0001

Data Index: 262119 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4030. Min Act: -0.0001

Data Index: 472432 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4069. Min Act: -0.0001

Data Index: 1354826 (C4 (Web Text))

Max Activating Token Index: 189