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

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

Neuron 6119 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8135. Min Range: -2.8135

Max Act: 2.8135. Min Act: -0.0000

Data Index: 1409731 (Python Code)

Max Activating Token Index: 909

Text #1

Max Range: 2.8135. Min Range: -2.8135

Max Act: 2.3593. Min Act: -0.0000

Data Index: 657368 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 2.8135. Min Range: -2.8135

Max Act: 2.4160. Min Act: -0.0000

Data Index: 600603 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 2.8135. Min Range: -2.8135

Max Act: 2.1166. Min Act: -0.0000

Data Index: 410636 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 2.8135. Min Range: -2.8135

Max Act: 2.2032. Min Act: -0.0000

Data Index: 83914 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 2.8135. Min Range: -2.8135

Max Act: 2.0228. Min Act: -0.0000

Data Index: 1390458 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.8082. Min Act: -0.0000

Data Index: 1426236 (Python Code)

Max Activating Token Index: 245

Text #7

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.9196. Min Act: -0.0000

Data Index: 1574770 (Python Code)

Max Activating Token Index: 451

Text #8

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.7755. Min Act: -0.0000

Data Index: 1399277 (Python Code)

Max Activating Token Index: 504

Text #9

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.8532. Min Act: -0.0000

Data Index: 1533132 (Python Code)

Max Activating Token Index: 661

Text #10

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.8527. Min Act: -0.0000

Data Index: 1524133 (Python Code)

Max Activating Token Index: 1012

Text #11

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.7263. Min Act: -0.0000

Data Index: 1619737 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.7441. Min Act: -0.0000

Data Index: 1638361 (Python Code)

Max Activating Token Index: 667

Text #13

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.6775. Min Act: -0.0000

Data Index: 1488887 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.6661. Min Act: -0.0000

Data Index: 1649645 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.6727. Min Act: -0.0000

Data Index: 1588171 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.7343. Min Act: -0.0000

Data Index: 1609416 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.6443. Min Act: 0.0000

Data Index: 1537015 (Python Code)

Max Activating Token Index: 349

Text #18

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.6144. Min Act: -0.0000

Data Index: 1395048 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 2.8135. Min Range: -2.8135

Max Act: 1.5272. Min Act: -0.0000

Data Index: 1396216 (Python Code)

Max Activating Token Index: 964