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

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

Neuron 2596 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2103. Min Range: -1.2103

Max Act: 1.2103. Min Act: -0.0001

Data Index: 1405842 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 1.2103. Min Range: -1.2103

Max Act: 1.1177. Min Act: -0.0001

Data Index: 1559399 (Python Code)

Max Activating Token Index: 449

Text #2

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.9017. Min Act: -0.0001

Data Index: 400238 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.9051. Min Act: -0.0001

Data Index: 663901 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.9517. Min Act: -0.0001

Data Index: 898305 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.8210. Min Act: -0.0001

Data Index: 497963 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.8202. Min Act: -0.0001

Data Index: 375503 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.8663. Min Act: -0.0001

Data Index: 1240475 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7875. Min Act: -0.0001

Data Index: 294467 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.8910. Min Act: -0.0001

Data Index: 926571 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.8163. Min Act: -0.0001

Data Index: 302731 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7673. Min Act: -0.0001

Data Index: 759832 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7632. Min Act: -0.0001

Data Index: 1139818 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.8098. Min Act: -0.0001

Data Index: 1272618 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7382. Min Act: -0.0001

Data Index: 1351947 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7879. Min Act: -0.0001

Data Index: 617884 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7306. Min Act: -0.0001

Data Index: 496430 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7143. Min Act: -0.0001

Data Index: 522795 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7578. Min Act: -0.0001

Data Index: 857564 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.2103. Min Range: -1.2103

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1159172 (C4 (Web Text))

Max Activating Token Index: 769