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

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

Neuron 3225 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: 1.2184. Min Range: -1.2184

Max Act: 1.2184. Min Act: -0.0000

Data Index: 351264 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.2092. Min Act: -0.0000

Data Index: 324671 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.1269. Min Act: -0.0000

Data Index: 468598 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.2184. Min Range: -1.2184

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1349055 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1029421 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9632. Min Act: -0.0000

Data Index: 218671 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9787. Min Act: -0.0000

Data Index: 257690 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9731. Min Act: -0.0000

Data Index: 388932 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9107. Min Act: -0.0000

Data Index: 359637 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9162. Min Act: -0.0000

Data Index: 349523 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1319356 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.9383. Min Act: -0.0000

Data Index: 14458 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8946. Min Act: -0.0000

Data Index: 871014 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8815. Min Act: -0.0000

Data Index: 381812 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.7896. Min Act: -0.0000

Data Index: 833669 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8131. Min Act: -0.0000

Data Index: 644085 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8293. Min Act: -0.0000

Data Index: 307189 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.7731. Min Act: -0.0000

Data Index: 440768 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.7995. Min Act: -0.0000

Data Index: 26957 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.2184. Min Range: -1.2184

Max Act: 0.8232. Min Act: -0.0000

Data Index: 211924 (C4 (Web Text))

Max Activating Token Index: 832