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

Dataset: The Pile

Neuron 653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.5634. Min Act: -0.0000

Data Index: 192176 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1839722 (The Pile)

Max Activating Token Index: 854

Text #2

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1287640 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1594577 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1637305 (The Pile)

Max Activating Token Index: 408

Text #5

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4520. Min Act: -0.0000

Data Index: 642690 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1336314 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1887484 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4548. Min Act: -0.0000

Data Index: 61443 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4514. Min Act: -0.0000

Data Index: 48228 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1230392 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4439. Min Act: -0.0000

Data Index: 625175 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1206155 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4285. Min Act: -0.0000

Data Index: 888910 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4406. Min Act: -0.0000

Data Index: 198345 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4405. Min Act: -0.0000

Data Index: 274943 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1954695 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1881171 (The Pile)

Max Activating Token Index: 392

Text #18

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4320. Min Act: -0.0000

Data Index: 409568 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 0.5634. Min Range: -0.5634

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1865322 (The Pile)

Max Activating Token Index: 540