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

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

Neuron 1728 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: 3.5126. Min Range: -3.5126

Max Act: 3.5126. Min Act: -0.0001

Data Index: 364876 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 3.5126. Min Range: -3.5126

Max Act: 3.4583. Min Act: -0.0001

Data Index: 1155525 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 3.5126. Min Range: -3.5126

Max Act: 3.0835. Min Act: -0.0001

Data Index: 997514 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 3.5126. Min Range: -3.5126

Max Act: 3.0401. Min Act: -0.0001

Data Index: 1085709 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 3.5126. Min Range: -3.5126

Max Act: 3.2227. Min Act: -0.0001

Data Index: 217451 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 3.5126. Min Range: -3.5126

Max Act: 3.1941. Min Act: -0.0001

Data Index: 909414 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 3.5126. Min Range: -3.5126

Max Act: 3.1540. Min Act: -0.0001

Data Index: 160224 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.8649. Min Act: -0.0001

Data Index: 1023430 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.5126. Min Range: -3.5126

Max Act: 3.0327. Min Act: -0.0001

Data Index: 1233407 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.8469. Min Act: -0.0001

Data Index: 526888 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.6985. Min Act: -0.0001

Data Index: 1197357 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.7172. Min Act: -0.0001

Data Index: 1315514 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.5392. Min Act: -0.0001

Data Index: 492002 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.9118. Min Act: -0.0001

Data Index: 173671 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.7542. Min Act: -0.0001

Data Index: 15679 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.7582. Min Act: -0.0001

Data Index: 514296 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.6452. Min Act: -0.0001

Data Index: 771285 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.8443. Min Act: -0.0001

Data Index: 774987 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.3544. Min Act: -0.0001

Data Index: 254245 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 3.5126. Min Range: -3.5126

Max Act: 2.8091. Min Act: -0.0001

Data Index: 289892 (C4 (Web Text))

Max Activating Token Index: 801