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

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

Neuron 3272 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7416. Min Act: -0.0000

Data Index: 201280 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8917. Min Act: -0.0000

Data Index: 1116409 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8152. Min Act: -0.0000

Data Index: 470604 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8135. Min Act: -0.0000

Data Index: 159534 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1182737 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1353186 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7305. Min Act: -0.0000

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7148. Min Act: -0.0000

Data Index: 437527 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7549. Min Act: -0.0000

Data Index: 491284 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6815. Min Act: -0.0000

Data Index: 430936 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6768. Min Act: -0.0000

Data Index: 673234 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.5458. Min Act: -0.0000

Data Index: 526383 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1008450 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7011. Min Act: -0.0000

Data Index: 681800 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7258. Min Act: -0.0000

Data Index: 175273 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6958. Min Act: -0.0000

Data Index: 499314 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1093282 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1223854 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6200. Min Act: -0.0000

Data Index: 666736 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6444. Min Act: -0.0000

Data Index: 1010278 (C4 (Web Text))

Max Activating Token Index: 746