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

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

Neuron 5761 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2082. Min Range: -3.2082

Max Act: 3.2082. Min Act: -0.0000

Data Index: 5432 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.8698. Min Act: -0.0000

Data Index: 1327606 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.2082. Min Range: -3.2082

Max Act: 3.0174. Min Act: -0.0000

Data Index: 795757 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.9223. Min Act: -0.0000

Data Index: 926193 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7172. Min Act: -0.0000

Data Index: 1328263 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.8137. Min Act: 0.0000

Data Index: 231206 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7770. Min Act: -0.0000

Data Index: 900222 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7694. Min Act: -0.0000

Data Index: 1253155 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7386. Min Act: -0.0000

Data Index: 294039 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7487. Min Act: 0.0000

Data Index: 1242274 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7211. Min Act: -0.0000

Data Index: 290453 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.8161. Min Act: -0.0000

Data Index: 449292 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.6674. Min Act: -0.0000

Data Index: 1158697 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7464. Min Act: -0.0000

Data Index: 950254 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7744. Min Act: -0.0000

Data Index: 1282598 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.6331. Min Act: -0.0000

Data Index: 1152966 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.7329. Min Act: -0.0000

Data Index: 701569 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.6122. Min Act: 0.0000

Data Index: 496713 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.5945. Min Act: -0.0000

Data Index: 1095151 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 3.2082. Min Range: -3.2082

Max Act: 2.4426. Min Act: -0.0000

Data Index: 1176074 (C4 (Web Text))

Max Activating Token Index: 966