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

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

Neuron 2489 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5158. Min Range: -1.5158

Max Act: 1.5158. Min Act: -0.0001

Data Index: 861245 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 1.5158. Min Range: -1.5158

Max Act: 1.2925. Min Act: -0.0001

Data Index: 635252 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.5158. Min Range: -1.5158

Max Act: 1.0921. Min Act: -0.0001

Data Index: 853205 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.5158. Min Range: -1.5158

Max Act: 1.1252. Min Act: -0.0001

Data Index: 989080 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.5158. Min Range: -1.5158

Max Act: 1.0632. Min Act: -0.0001

Data Index: 1090494 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.5158. Min Range: -1.5158

Max Act: 1.0268. Min Act: -0.0001

Data Index: 1003424 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.9916. Min Act: -0.0001

Data Index: 1259926 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.9495. Min Act: -0.0001

Data Index: 212334 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.9379. Min Act: -0.0001

Data Index: 438534 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.8630. Min Act: -0.0001

Data Index: 618723 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.7749. Min Act: -0.0001

Data Index: 839554 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.8668. Min Act: -0.0001

Data Index: 202822 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.8610. Min Act: -0.0001

Data Index: 1082188 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.8574. Min Act: -0.0001

Data Index: 1072211 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.9142. Min Act: -0.0001

Data Index: 655081 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.8412. Min Act: -0.0001

Data Index: 40870 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.8550. Min Act: -0.0001

Data Index: 301367 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.7544. Min Act: -0.0001

Data Index: 440449 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.9039. Min Act: -0.0001

Data Index: 919721 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.5158. Min Range: -1.5158

Max Act: 0.8191. Min Act: -0.0001

Data Index: 258889 (C4 (Web Text))

Max Activating Token Index: 500