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

Dataset: The Pile

Neuron 1234 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: 1.8787. Min Range: -1.8787

Max Act: 1.8787. Min Act: -0.0000

Data Index: 378057 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.6213. Min Act: -0.0000

Data Index: 1645391 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.5126. Min Act: -0.0000

Data Index: 1826019 (The Pile)

Max Activating Token Index: 95

Text #3

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.3334. Min Act: -0.0000

Data Index: 852396 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.1712. Min Act: -0.0000

Data Index: 251035 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.4085. Min Act: -0.0000

Data Index: 803357 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.1957. Min Act: -0.0000

Data Index: 899546 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.2297. Min Act: -0.0000

Data Index: 152287 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.0253. Min Act: -0.0000

Data Index: 871216 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.0587. Min Act: -0.0000

Data Index: 148328 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.0929. Min Act: -0.0000

Data Index: 229404 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 1.8787. Min Range: -1.8787

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1421071 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.0536. Min Act: -0.0000

Data Index: 73940 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1464029 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 1.8787. Min Range: -1.8787

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1510225 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 1.8787. Min Range: -1.8787

Max Act: 0.9738. Min Act: -0.0000

Data Index: 235242 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.0289. Min Act: -0.0000

Data Index: 376700 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 1.8787. Min Range: -1.8787

Max Act: 0.8513. Min Act: -0.0000

Data Index: 249629 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 1.8787. Min Range: -1.8787

Max Act: 0.9985. Min Act: -0.0000

Data Index: 734170 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 1.8787. Min Range: -1.8787

Max Act: 1.0034. Min Act: -0.0000

Data Index: 407431 (The Pile)

Max Activating Token Index: 1022