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

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

Neuron 2102 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1403514 (Python Code)

Max Activating Token Index: 904

Text #1

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5161. Min Act: -0.0001

Data Index: 614376 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5002. Min Act: -0.0001

Data Index: 1438853 (Python Code)

Max Activating Token Index: 827

Text #3

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5117. Min Act: -0.0001

Data Index: 1008427 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4905. Min Act: -0.0001

Data Index: 1466164 (Python Code)

Max Activating Token Index: 1006

Text #5

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4698. Min Act: -0.0001

Data Index: 440565 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4695. Min Act: -0.0001

Data Index: 1524419 (Python Code)

Max Activating Token Index: 1002

Text #7

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4522. Min Act: -0.0001

Data Index: 76722 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4320. Min Act: -0.0001

Data Index: 1595798 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4331. Min Act: -0.0001

Data Index: 58905 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4455. Min Act: -0.0001

Data Index: 632819 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4581. Min Act: -0.0001

Data Index: 1158055 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4277. Min Act: -0.0001

Data Index: 1372414 (Python Code)

Max Activating Token Index: 348

Text #13

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1616554 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4564. Min Act: -0.0001

Data Index: 1599360 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4242. Min Act: -0.0001

Data Index: 179041 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1372193 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4420. Min Act: -0.0001

Data Index: 1511511 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4134. Min Act: -0.0001

Data Index: 1623781 (Python Code)

Max Activating Token Index: 867

Text #19

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4105. Min Act: -0.0001

Data Index: 111644 (C4 (Web Text))

Max Activating Token Index: 199