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

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

Neuron 1331 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.5948. Min Act: -0.0001

Data Index: 12433 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4044. Min Act: -0.0001

Data Index: 962291 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4595. Min Act: -0.0001

Data Index: 442202 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4047. Min Act: -0.0000

Data Index: 492528 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4622. Min Act: -0.0001

Data Index: 597744 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1327808 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3947. Min Act: -0.0001

Data Index: 42286 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3408. Min Act: -0.0001

Data Index: 789474 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4222. Min Act: -0.0001

Data Index: 318926 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.4105. Min Act: -0.0001

Data Index: 344896 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1467. Min Act: -0.0001

Data Index: 665529 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2871. Min Act: -0.0000

Data Index: 144682 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3960. Min Act: -0.0000

Data Index: 491663 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2771. Min Act: -0.0001

Data Index: 424976 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3172. Min Act: -0.0000

Data Index: 370887 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3103. Min Act: -0.0000

Data Index: 1169338 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.1854. Min Act: -0.0000

Data Index: 644556 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.3122. Min Act: -0.0001

Data Index: 381473 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2579. Min Act: -0.0001

Data Index: 771504 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.5948. Min Range: -1.5948

Max Act: 1.2273. Min Act: -0.0000

Data Index: 263056 (C4 (Web Text))

Max Activating Token Index: 21