Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4034 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.3299. Min Act: -0.0000

Data Index: 869940 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2853. Min Act: -0.0000

Data Index: 427946 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2871. Min Act: -0.0000

Data Index: 930882 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2524. Min Act: -0.0000

Data Index: 979472 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1269630 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2570. Min Act: -0.0000

Data Index: 983965 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2393. Min Act: -0.0000

Data Index: 457865 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2266. Min Act: -0.0000

Data Index: 630303 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2100. Min Act: -0.0000

Data Index: 563601 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2291. Min Act: -0.0000

Data Index: 665281 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2068. Min Act: -0.0000

Data Index: 743582 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1026285 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2169. Min Act: -0.0000

Data Index: 359293 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2059. Min Act: -0.0000

Data Index: 738952 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1313052 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2213. Min Act: -0.0000

Data Index: 217457 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1347656 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.1901. Min Act: -0.0000

Data Index: 582619 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2152. Min Act: -0.0000

Data Index: 952926 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.3299. Min Range: -0.3299

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1004077 (C4 (Web Text))

Max Activating Token Index: 152