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

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

Neuron 304 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: 0.3765. Min Range: -0.3765

Max Act: 0.3765. Min Act: -0.0001

Data Index: 1547412 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.3199. Min Act: -0.0001

Data Index: 1405873 (Python Code)

Max Activating Token Index: 348

Text #2

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.3414. Min Act: -0.0001

Data Index: 1461448 (Python Code)

Max Activating Token Index: 480

Text #3

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.3166. Min Act: -0.0001

Data Index: 860388 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.3247. Min Act: 0.0002

Data Index: 1629711 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2953. Min Act: -0.0001

Data Index: 1588239 (Python Code)

Max Activating Token Index: 560

Text #6

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1447104 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2786. Min Act: 0.0001

Data Index: 1644329 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2774. Min Act: 0.0000

Data Index: 1564530 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1060610 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2835. Min Act: -0.0001

Data Index: 603237 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2498. Min Act: 0.0001

Data Index: 1587306 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1594027 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2733. Min Act: -0.0001

Data Index: 1555826 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2455. Min Act: 0.0000

Data Index: 1566602 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1647458 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2617. Min Act: 0.0000

Data Index: 1597723 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2865. Min Act: -0.0000

Data Index: 1330187 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2846. Min Act: -0.0001

Data Index: 1410577 (Python Code)

Max Activating Token Index: 883

Text #19

Max Range: 0.3765. Min Range: -0.3765

Max Act: 0.2667. Min Act: 0.0001

Data Index: 1536932 (Python Code)

Max Activating Token Index: 741