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

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

Neuron 3250 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1442954 (Python Code)

Max Activating Token Index: 988

Text #1

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1373720 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1372462 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1492404 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3686. Min Act: -0.0001

Data Index: 1477536 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3609. Min Act: -0.0001

Data Index: 1474642 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3461. Min Act: -0.0001

Data Index: 1366347 (Python Code)

Max Activating Token Index: 736

Text #7

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1509065 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1518079 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1613156 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1461146 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1475725 (Python Code)

Max Activating Token Index: 579

Text #12

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1568315 (Python Code)

Max Activating Token Index: 665

Text #13

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1576583 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1492078 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3022. Min Act: -0.0001

Data Index: 1400088 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1599820 (Python Code)

Max Activating Token Index: 312

Text #17

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3347. Min Act: -0.0001

Data Index: 1498296 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1365394 (Python Code)

Max Activating Token Index: 610

Text #19

Max Range: 0.4241. Min Range: -0.4241

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1414029 (Python Code)

Max Activating Token Index: 920