Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2002 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.3924. Min Act: -0.0001

Data Index: 234333 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.4217. Min Act: -0.0001

Data Index: 1167804 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.2241. Min Act: -0.0001

Data Index: 1142208 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.0736. Min Act: -0.0001

Data Index: 1349186 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.0312. Min Act: -0.0001

Data Index: 539274 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.0435. Min Act: -0.0001

Data Index: 795116 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.0470. Min Act: -0.0001

Data Index: 88047 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9108. Min Act: -0.0001

Data Index: 174028 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9237. Min Act: -0.0001

Data Index: 882258 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9138. Min Act: -0.0001

Data Index: 973862 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8894. Min Act: -0.0001

Data Index: 168911 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9146. Min Act: -0.0001

Data Index: 748329 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1053362 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8811. Min Act: -0.0000

Data Index: 525694 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1269363 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8403. Min Act: -0.0001

Data Index: 94515 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8537. Min Act: -0.0001

Data Index: 1495261 (Python Code)

Max Activating Token Index: 236

Text #17

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8422. Min Act: -0.0000

Data Index: 462457 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.7637. Min Act: -0.0001

Data Index: 482185 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8654. Min Act: -0.0000

Data Index: 918803 (C4 (Web Text))

Max Activating Token Index: 402