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

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

Neuron 597 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.3033. Min Act: -0.0000

Data Index: 646104 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1178903 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1334887 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2757. Min Act: -0.0000

Data Index: 799945 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2786. Min Act: -0.0000

Data Index: 920086 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2545. Min Act: -0.0000

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2365. Min Act: -0.0000

Data Index: 792122 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2351. Min Act: -0.0000

Data Index: 664090 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2378. Min Act: -0.0000

Data Index: 7591 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2267. Min Act: -0.0000

Data Index: 43049 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1201670 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2130. Min Act: -0.0000

Data Index: 278797 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2198. Min Act: -0.0000

Data Index: 1331082 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2171. Min Act: -0.0000

Data Index: 168218 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2043. Min Act: -0.0000

Data Index: 116280 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1305373 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.1966. Min Act: -0.0000

Data Index: 431923 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2072. Min Act: -0.0000

Data Index: 87546 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.2111. Min Act: -0.0000

Data Index: 132054 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.3033. Min Range: -0.3033

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1045308 (C4 (Web Text))

Max Activating Token Index: 568