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

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

Neuron 1427 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.3041. Min Act: -0.0001

Data Index: 371848 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.1317. Min Act: -0.0001

Data Index: 1222739 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.1134. Min Act: -0.0001

Data Index: 1045197 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.3041. Min Range: -1.3041

Max Act: 1.0501. Min Act: -0.0001

Data Index: 560408 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9673. Min Act: -0.0001

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9380. Min Act: -0.0001

Data Index: 1129201 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9526. Min Act: -0.0001

Data Index: 142880 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9277. Min Act: -0.0001

Data Index: 176440 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8818. Min Act: -0.0001

Data Index: 1046651 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9125. Min Act: -0.0001

Data Index: 1144336 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9079. Min Act: -0.0001

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9316. Min Act: -0.0001

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8842. Min Act: -0.0001

Data Index: 213810 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8623. Min Act: -0.0001

Data Index: 440294 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8060. Min Act: -0.0001

Data Index: 1431397 (Python Code)

Max Activating Token Index: 831

Text #15

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8259. Min Act: -0.0001

Data Index: 1573368 (Python Code)

Max Activating Token Index: 876

Text #16

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.9008. Min Act: -0.0001

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1086041 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8174. Min Act: -0.0001

Data Index: 1431627 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 1.3041. Min Range: -1.3041

Max Act: 0.8371. Min Act: -0.0001

Data Index: 536126 (C4 (Web Text))

Max Activating Token Index: 907