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

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

Neuron 1217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.4241. Min Range: -5.4241

Max Act: 5.4241. Min Act: -0.0000

Data Index: 58475 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 5.4241. Min Range: -5.4241

Max Act: 5.1788. Min Act: -0.0000

Data Index: 76641 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 5.4241. Min Range: -5.4241

Max Act: 5.1283. Min Act: -0.0000

Data Index: 398433 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 5.4241. Min Range: -5.4241

Max Act: 4.9157. Min Act: -0.0000

Data Index: 224289 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 5.4241. Min Range: -5.4241

Max Act: 4.8917. Min Act: -0.0000

Data Index: 1215845 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 5.4241. Min Range: -5.4241

Max Act: 4.5518. Min Act: -0.0000

Data Index: 560127 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 5.4241. Min Range: -5.4241

Max Act: 4.2744. Min Act: -0.0000

Data Index: 166838 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 5.4241. Min Range: -5.4241

Max Act: 3.9432. Min Act: -0.0000

Data Index: 665706 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 5.4241. Min Range: -5.4241

Max Act: 3.8301. Min Act: -0.0000

Data Index: 750320 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.9529. Min Act: -0.0000

Data Index: 409494 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.8673. Min Act: -0.0000

Data Index: 906062 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 5.4241. Min Range: -5.4241

Max Act: 3.1199. Min Act: -0.0000

Data Index: 172555 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.6664. Min Act: -0.0000

Data Index: 478885 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.7150. Min Act: -0.0000

Data Index: 500799 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.8181. Min Act: -0.0000

Data Index: 961626 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.9450. Min Act: -0.0000

Data Index: 217418 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.5108. Min Act: -0.0000

Data Index: 337177 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 5.4241. Min Range: -5.4241

Max Act: 3.0816. Min Act: -0.0000

Data Index: 746546 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.3901. Min Act: -0.0000

Data Index: 612680 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 5.4241. Min Range: -5.4241

Max Act: 2.4780. Min Act: -0.0000

Data Index: 362709 (C4 (Web Text))

Max Activating Token Index: 92