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

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

Neuron 4647 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: 1.7952. Min Range: -1.7952

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1463014 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 1.7952. Min Range: -1.7952

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1502071 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 1.7952. Min Range: -1.7952

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1625540 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1580679 (Python Code)

Max Activating Token Index: 208

Text #4

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.7517. Min Act: -0.0000

Data Index: 1601560 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1621356 (Python Code)

Max Activating Token Index: 511

Text #6

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1461766 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1414883 (Python Code)

Max Activating Token Index: 920

Text #8

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1503389 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1396379 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1400432 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1476428 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1422307 (Python Code)

Max Activating Token Index: 358

Text #13

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1412072 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1376419 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1402015 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1650452 (Python Code)

Max Activating Token Index: 453

Text #17

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1475744 (Python Code)

Max Activating Token Index: 893

Text #18

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1440373 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 1.7952. Min Range: -1.7952

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1490022 (Python Code)

Max Activating Token Index: 145