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

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

Neuron 2632 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2100. Min Range: -3.2100

Max Act: 3.2100. Min Act: -0.0000

Data Index: 1618666 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.4804. Min Act: -0.0000

Data Index: 1634140 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.4540. Min Act: -0.0000

Data Index: 1505514 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.4519. Min Act: -0.0000

Data Index: 1563507 (Python Code)

Max Activating Token Index: 525

Text #4

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.5174. Min Act: -0.0000

Data Index: 892171 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.2772. Min Act: -0.0000

Data Index: 835245 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.2335. Min Act: -0.0000

Data Index: 1102323 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.0933. Min Act: -0.0000

Data Index: 1458216 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.4396. Min Act: -0.0000

Data Index: 1483561 (Python Code)

Max Activating Token Index: 1008

Text #9

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.4863. Min Act: -0.0000

Data Index: 1588081 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.0363. Min Act: -0.0000

Data Index: 1237989 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.2149. Min Act: -0.0000

Data Index: 1444913 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.1682. Min Act: -0.0000

Data Index: 1623061 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.2642. Min Act: -0.0000

Data Index: 1444397 (Python Code)

Max Activating Token Index: 201

Text #14

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.0352. Min Act: -0.0000

Data Index: 49588 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.0745. Min Act: -0.0000

Data Index: 473360 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.1529. Min Act: -0.0000

Data Index: 1489445 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.1398. Min Act: -0.0000

Data Index: 1084110 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 3.2100. Min Range: -3.2100

Max Act: 1.9240. Min Act: -0.0000

Data Index: 814259 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 3.2100. Min Range: -3.2100

Max Act: 2.0995. Min Act: -0.0000

Data Index: 1377529 (Python Code)

Max Activating Token Index: 302