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

Dataset: The Pile

Neuron 4611 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: 0.9080. Min Range: -0.9080

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1044906 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8872. Min Act: -0.0000

Data Index: 655736 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1435782 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1160723 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8523. Min Act: -0.0000

Data Index: 201626 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1159003 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8075. Min Act: -0.0000

Data Index: 291476 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7376. Min Act: -0.0000

Data Index: 276204 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7770. Min Act: -0.0000

Data Index: 350542 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1597707 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1176905 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7679. Min Act: -0.0000

Data Index: 489068 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8102. Min Act: -0.0000

Data Index: 130902 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6952. Min Act: -0.0000

Data Index: 12236 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1633233 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1142497 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7659. Min Act: -0.0000

Data Index: 707952 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7254. Min Act: -0.0000

Data Index: 529366 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.7068. Min Act: -0.0000

Data Index: 383091 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 0.9080. Min Range: -0.9080

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1636345 (The Pile)

Max Activating Token Index: 645