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

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

Neuron 1390 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: 3.0124. Min Range: -3.0124

Max Act: 3.0124. Min Act: -0.0001

Data Index: 358562 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.0124. Min Range: -3.0124

Max Act: 2.3112. Min Act: -0.0001

Data Index: 558261 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.0124. Min Range: -3.0124

Max Act: 2.1759. Min Act: -0.0001

Data Index: 953773 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 3.0124. Min Range: -3.0124

Max Act: 2.3618. Min Act: -0.0001

Data Index: 1058770 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.7274. Min Act: -0.0001

Data Index: 1238558 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.9662. Min Act: -0.0001

Data Index: 123151 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 3.0124. Min Range: -3.0124

Max Act: 2.0554. Min Act: -0.0001

Data Index: 49565 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.7280. Min Act: -0.0001

Data Index: 708790 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.7974. Min Act: -0.0001

Data Index: 674418 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.8881. Min Act: -0.0001

Data Index: 430438 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 3.0124. Min Range: -3.0124

Max Act: 2.1001. Min Act: -0.0001

Data Index: 161850 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.5956. Min Act: -0.0001

Data Index: 934557 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.3459. Min Act: -0.0001

Data Index: 364990 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.9266. Min Act: -0.0001

Data Index: 1194169 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.6961. Min Act: -0.0001

Data Index: 586735 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.6889. Min Act: -0.0001

Data Index: 978717 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.9331. Min Act: -0.0001

Data Index: 304007 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.7822. Min Act: -0.0001

Data Index: 1326974 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.7635. Min Act: -0.0001

Data Index: 1107283 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 3.0124. Min Range: -3.0124

Max Act: 1.7596. Min Act: -0.0001

Data Index: 356519 (C4 (Web Text))

Max Activating Token Index: 504