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

Dataset: The Pile

Neuron 1517 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1600580 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1743367 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1379. Min Act: -0.0000

Data Index: 985992 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1257. Min Act: -0.0000

Data Index: 98226 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1280. Min Act: -0.0000

Data Index: 285854 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1186577 (The Pile)

Max Activating Token Index: 802

Text #6

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1199. Min Act: -0.0000

Data Index: 542326 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1445695 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1395790 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1080680 (The Pile)

Max Activating Token Index: 804

Text #10

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1223115 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1060. Min Act: -0.0000

Data Index: 78892 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1392408 (The Pile)

Max Activating Token Index: 637

Text #13

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1130. Min Act: -0.0000

Data Index: 1536290 (The Pile)

Max Activating Token Index: 213

Text #14

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1993539 (The Pile)

Max Activating Token Index: 771

Text #15

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1922001 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1035. Min Act: -0.0000

Data Index: 966149 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1040312 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0897. Min Act: -0.0000

Data Index: 777099 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0988. Min Act: -0.0000

Data Index: 611043 (The Pile)

Max Activating Token Index: 545