Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1846 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2614. Min Act: -0.0000

Data Index: 142572 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1338718 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1770283 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1293752 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2391. Min Act: -0.0000

Data Index: 786154 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1439109 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2417. Min Act: -0.0000

Data Index: 453891 (The Pile)

Max Activating Token Index: 938

Text #7

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2340. Min Act: -0.0000

Data Index: 50422 (The Pile)

Max Activating Token Index: 829

Text #8

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1637935 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1890621 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2378. Min Act: -0.0000

Data Index: 793595 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1874914 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1118236 (The Pile)

Max Activating Token Index: 281

Text #13

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2409. Min Act: -0.0000

Data Index: 293710 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2335. Min Act: -0.0000

Data Index: 1285467 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2298. Min Act: -0.0000

Data Index: 920 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1827112 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1313281 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1702305 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 0.2614. Min Range: -0.2614

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1539953 (The Pile)

Max Activating Token Index: 982