Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4408 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.6241. Min Act: -0.0001

Data Index: 846582 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.5195. Min Act: -0.0001

Data Index: 642973 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4881. Min Act: -0.0001

Data Index: 622578 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1343670 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4522. Min Act: -0.0001

Data Index: 1050358 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1171363 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4540. Min Act: -0.0001

Data Index: 762618 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4436. Min Act: -0.0001

Data Index: 1335945 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4450. Min Act: -0.0001

Data Index: 861579 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4289. Min Act: -0.0001

Data Index: 863185 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4306. Min Act: -0.0001

Data Index: 1230016 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4265. Min Act: -0.0001

Data Index: 1185012 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4352. Min Act: -0.0001

Data Index: 418478 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4196. Min Act: -0.0001

Data Index: 801843 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4226. Min Act: -0.0001

Data Index: 1188927 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4293. Min Act: -0.0001

Data Index: 516146 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4255. Min Act: -0.0001

Data Index: 1111887 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1296344 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4241. Min Act: -0.0001

Data Index: 923286 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.6241. Min Range: -0.6241

Max Act: 0.4306. Min Act: -0.0001

Data Index: 1028695 (C4 (Web Text))

Max Activating Token Index: 776