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

Dataset: The Pile

Neuron 1843 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2379. Min Range: -1.2379

Max Act: 1.2379. Min Act: -0.0000

Data Index: 1934036 (The Pile)

Max Activating Token Index: 205

Text #1

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9454. Min Act: -0.0000

Data Index: 331304 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9937. Min Act: -0.0000

Data Index: 977804 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1723501 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9805. Min Act: -0.0000

Data Index: 654332 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1460106 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1243550 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.9338. Min Act: -0.0000

Data Index: 974012 (The Pile)

Max Activating Token Index: 395

Text #8

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8475. Min Act: -0.0000

Data Index: 600543 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1581395 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1488300 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8531. Min Act: -0.0000

Data Index: 455013 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8135. Min Act: -0.0000

Data Index: 811195 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1376751 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1379981 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8447. Min Act: -0.0000

Data Index: 356961 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.8356. Min Act: -0.0000

Data Index: 510175 (The Pile)

Max Activating Token Index: 902

Text #17

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1392451 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.7696. Min Act: -0.0000

Data Index: 135231 (The Pile)

Max Activating Token Index: 482

Text #19

Max Range: 1.2379. Min Range: -1.2379

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1863880 (The Pile)

Max Activating Token Index: 694