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

Dataset: The Pile

Neuron 4874 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: 1.3441. Min Range: -1.3441

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1240551 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.2175. Min Act: -0.0000

Data Index: 710749 (The Pile)

Max Activating Token Index: 169

Text #2

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1804355 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.1673. Min Act: -0.0000

Data Index: 324933 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.1132. Min Act: -0.0000

Data Index: 94480 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0627. Min Act: -0.0000

Data Index: 689039 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1545596 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1719518 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1852734 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9288. Min Act: -0.0000

Data Index: 982907 (The Pile)

Max Activating Token Index: 829

Text #10

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1662965 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1946802 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1429189 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 1.3441. Min Range: -1.3441

Max Act: 1.0325. Min Act: -0.0000

Data Index: 142920 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9691. Min Act: -0.0000

Data Index: 8253 (The Pile)

Max Activating Token Index: 497

Text #15

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9009. Min Act: -0.0000

Data Index: 699140 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9495. Min Act: -0.0000

Data Index: 498426 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.9133. Min Act: -0.0000

Data Index: 200856 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.8892. Min Act: -0.0000

Data Index: 646116 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 1.3441. Min Range: -1.3441

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1849264 (The Pile)

Max Activating Token Index: 470