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

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

Neuron 4236 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3968. Min Act: -0.0002

Data Index: 1436229 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3594. Min Act: -0.0002

Data Index: 1370223 (Python Code)

Max Activating Token Index: 837

Text #2

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3450. Min Act: -0.0002

Data Index: 1552052 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3443. Min Act: -0.0002

Data Index: 1597355 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3248. Min Act: -0.0002

Data Index: 1508447 (Python Code)

Max Activating Token Index: 448

Text #5

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3260. Min Act: -0.0002

Data Index: 1643946 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3193. Min Act: -0.0002

Data Index: 1444290 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3168. Min Act: -0.0002

Data Index: 1023393 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3031. Min Act: -0.0002

Data Index: 1567927 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3040. Min Act: -0.0002

Data Index: 1604456 (Python Code)

Max Activating Token Index: 182

Text #10

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2962. Min Act: -0.0002

Data Index: 123487 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.3064. Min Act: -0.0002

Data Index: 1417595 (Python Code)

Max Activating Token Index: 413

Text #12

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2923. Min Act: -0.0002

Data Index: 1195282 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2907. Min Act: -0.0002

Data Index: 1409291 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2790. Min Act: -0.0002

Data Index: 1431443 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2955. Min Act: -0.0002

Data Index: 654028 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2757. Min Act: -0.0002

Data Index: 1095689 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2834. Min Act: -0.0002

Data Index: 17412 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2788. Min Act: -0.0002

Data Index: 1393056 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 0.3968. Min Range: -0.3968

Max Act: 0.2863. Min Act: -0.0002

Data Index: 1157528 (C4 (Web Text))

Max Activating Token Index: 1009