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

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

Neuron 3246 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: 2.6263. Min Range: -2.6263

Max Act: 2.4683. Min Act: -0.0001

Data Index: 1406758 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.1594. Min Act: -0.0000

Data Index: 363383 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.2428. Min Act: -0.0000

Data Index: 100667 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.2107. Min Act: -0.0000

Data Index: 1387448 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.1044. Min Act: -0.0001

Data Index: 1178985 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1287320 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.3093. Min Act: -0.0000

Data Index: 1147624 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.1829. Min Act: -0.0000

Data Index: 1156676 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.2949. Min Act: -0.0000

Data Index: 1575649 (Python Code)

Max Activating Token Index: 657

Text #9

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.2631. Min Act: -0.0001

Data Index: 1393673 (Python Code)

Max Activating Token Index: 554

Text #10

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.1219. Min Act: -0.0001

Data Index: 1371942 (Python Code)

Max Activating Token Index: 552

Text #11

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.2152. Min Act: -0.0001

Data Index: 1495084 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.0958. Min Act: -0.0001

Data Index: 1402363 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.6263. Min Act: -0.0000

Data Index: 1638118 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.0584. Min Act: -0.0000

Data Index: 1432714 (Python Code)

Max Activating Token Index: 339

Text #15

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.2602. Min Act: -0.0001

Data Index: 1532572 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.0320. Min Act: -0.0000

Data Index: 1655028 (Python Code)

Max Activating Token Index: 341

Text #17

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.0124. Min Act: -0.0000

Data Index: 137445 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 2.6263. Min Range: -2.6263

Max Act: 2.0136. Min Act: -0.0000

Data Index: 1575502 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 2.6263. Min Range: -2.6263

Max Act: 1.9928. Min Act: -0.0000

Data Index: 911588 (C4 (Web Text))

Max Activating Token Index: 756