Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.4045. Min Act: -0.0002

Data Index: 1428402 (Python Code)

Max Activating Token Index: 919

Text #1

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3922. Min Act: -0.0001

Data Index: 1382571 (Python Code)

Max Activating Token Index: 275

Text #2

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3690. Min Act: -0.0002

Data Index: 1466622 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3105. Min Act: -0.0002

Data Index: 1543821 (Python Code)

Max Activating Token Index: 959

Text #4

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1592836 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3189. Min Act: -0.0001

Data Index: 1461102 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3069. Min Act: -0.0002

Data Index: 1613594 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3161. Min Act: -0.0002

Data Index: 1597732 (Python Code)

Max Activating Token Index: 934

Text #8

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3142. Min Act: -0.0002

Data Index: 1511814 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1617434 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3067. Min Act: -0.0001

Data Index: 1370778 (Python Code)

Max Activating Token Index: 940

Text #11

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3137. Min Act: -0.0001

Data Index: 1593119 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3257. Min Act: -0.0002

Data Index: 1605300 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3150. Min Act: -0.0001

Data Index: 1407552 (Python Code)

Max Activating Token Index: 637

Text #14

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3010. Min Act: -0.0002

Data Index: 1656627 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1634397 (Python Code)

Max Activating Token Index: 954

Text #16

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3113. Min Act: -0.0001

Data Index: 1434875 (Python Code)

Max Activating Token Index: 817

Text #17

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1452473 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3097. Min Act: -0.0002

Data Index: 1490229 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3194. Min Act: -0.0002

Data Index: 1552213 (Python Code)

Max Activating Token Index: 1002