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

Dataset: The Pile

Neuron 2268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5316. Min Act: -0.0000

Data Index: 116242 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5797. Min Act: -0.0000

Data Index: 815632 (The Pile)

Max Activating Token Index: 535

Text #2

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1266768 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1068986 (The Pile)

Max Activating Token Index: 235

Text #4

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1543333 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5223. Min Act: -0.0000

Data Index: 347145 (The Pile)

Max Activating Token Index: 427

Text #6

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1448518 (The Pile)

Max Activating Token Index: 625

Text #7

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1814612 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1377112 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4627. Min Act: -0.0000

Data Index: 783383 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1294883 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1070055 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1706482 (The Pile)

Max Activating Token Index: 363

Text #13

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4095. Min Act: -0.0000

Data Index: 667653 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.3770. Min Act: -0.0000

Data Index: 208105 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1826867 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1014958 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1775987 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.4505. Min Act: -0.0000

Data Index: 389949 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 0.5956. Min Range: -0.5956

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1573118 (The Pile)

Max Activating Token Index: 617