Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2938 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1613747 (Python Code)

Max Activating Token Index: 516

Text #1

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3444. Min Act: -0.0001

Data Index: 1637022 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3450. Min Act: -0.0001

Data Index: 1460547 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1597185 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3269. Min Act: -0.0001

Data Index: 1468413 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3263. Min Act: -0.0001

Data Index: 1541790 (Python Code)

Max Activating Token Index: 926

Text #6

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1389717 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2950. Min Act: -0.0001

Data Index: 1458094 (Python Code)

Max Activating Token Index: 925

Text #8

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1512588 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2910. Min Act: -0.0001

Data Index: 1474179 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2889. Min Act: -0.0001

Data Index: 1531527 (Python Code)

Max Activating Token Index: 1022

Text #11

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1626344 (Python Code)

Max Activating Token Index: 738

Text #12

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3177. Min Act: -0.0001

Data Index: 1606333 (Python Code)

Max Activating Token Index: 827

Text #13

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1363415 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2719. Min Act: -0.0001

Data Index: 1431391 (Python Code)

Max Activating Token Index: 906

Text #15

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1502710 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1495774 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2598. Min Act: -0.0001

Data Index: 1472461 (Python Code)

Max Activating Token Index: 57

Text #18

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2010. Min Act: -0.0001

Data Index: 1506488 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1575510 (Python Code)

Max Activating Token Index: 1007