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

Dataset: The Pile

Neuron 1184 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: 0.9056. Min Range: -0.9056

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1515214 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1140788 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1646291 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1093315 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1079859 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1164968 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1836198 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7485. Min Act: -0.0000

Data Index: 79504 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7089. Min Act: -0.0000

Data Index: 855055 (The Pile)

Max Activating Token Index: 313

Text #9

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1214525 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7504. Min Act: -0.0000

Data Index: 222881 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7452. Min Act: -0.0000

Data Index: 638234 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1338321 (The Pile)

Max Activating Token Index: 571

Text #13

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1773275 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6604. Min Act: -0.0000

Data Index: 573029 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6956. Min Act: -0.0000

Data Index: 792572 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1186482 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1092883 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6955. Min Act: 0.0000

Data Index: 22044 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 0.9056. Min Range: -0.9056

Max Act: 0.6445. Min Act: -0.0000

Data Index: 567675 (The Pile)

Max Activating Token Index: 831