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

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

Neuron 4206 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1491295 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.6114. Min Act: -0.0000

Data Index: 1443497 (Python Code)

Max Activating Token Index: 886

Text #2

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1440188 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.5276. Min Act: -0.0000

Data Index: 1421453 (Python Code)

Max Activating Token Index: 189

Text #4

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1375371 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.2604. Min Act: -0.0000

Data Index: 1643805 (Python Code)

Max Activating Token Index: 997

Text #6

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1439999 (Python Code)

Max Activating Token Index: 838

Text #7

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1445869 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1464357 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1507583 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1461910 (Python Code)

Max Activating Token Index: 740

Text #11

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1484080 (Python Code)

Max Activating Token Index: 571

Text #12

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1404786 (Python Code)

Max Activating Token Index: 672

Text #13

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1400849 (Python Code)

Max Activating Token Index: 944

Text #14

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1564111 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 1.6114. Min Range: -1.6114

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1489831 (Python Code)

Max Activating Token Index: 721

Text #16

Max Range: 1.6114. Min Range: -1.6114

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1416325 (Python Code)

Max Activating Token Index: 321

Text #17

Max Range: 1.6114. Min Range: -1.6114

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1440391 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 1.6114. Min Range: -1.6114

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1494748 (Python Code)

Max Activating Token Index: 229

Text #19

Max Range: 1.6114. Min Range: -1.6114

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1383518 (Python Code)

Max Activating Token Index: 736