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

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

Neuron 3430 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0483. Min Range: -2.0483

Max Act: 2.0078. Min Act: -0.0000

Data Index: 1287503 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 2.0483. Min Range: -2.0483

Max Act: 2.0476. Min Act: -0.0000

Data Index: 1171593 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.8930. Min Act: -0.0000

Data Index: 367340 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.9850. Min Act: -0.0000

Data Index: 800388 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 2.0483. Min Range: -2.0483

Max Act: 2.0483. Min Act: -0.0000

Data Index: 38651 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.7842. Min Act: -0.0000

Data Index: 524767 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.8671. Min Act: -0.0000

Data Index: 270146 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.9767. Min Act: -0.0000

Data Index: 1174820 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.9402. Min Act: -0.0000

Data Index: 642259 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.8272. Min Act: -0.0000

Data Index: 486230 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.8178. Min Act: -0.0000

Data Index: 1006730 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.7643. Min Act: -0.0000

Data Index: 1223077 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.8150. Min Act: -0.0000

Data Index: 251451 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.7056. Min Act: -0.0000

Data Index: 787207 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.5864. Min Act: -0.0000

Data Index: 564839 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.5694. Min Act: -0.0000

Data Index: 989967 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.5314. Min Act: -0.0000

Data Index: 800183 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.4434. Min Act: -0.0000

Data Index: 367508 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1072125 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 2.0483. Min Range: -2.0483

Max Act: 1.1652. Min Act: -0.0000

Data Index: 719343 (C4 (Web Text))

Max Activating Token Index: 271