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

Dataset: The Pile

Neuron 4314 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.9308. Min Act: -0.0000

Data Index: 1441007 (The Pile)

Max Activating Token Index: 869

Text #1

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8280. Min Act: -0.0000

Data Index: 235293 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1143481 (The Pile)

Max Activating Token Index: 990

Text #3

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1821904 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1826699 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1987412 (The Pile)

Max Activating Token Index: 411

Text #6

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7226. Min Act: -0.0000

Data Index: 386474 (The Pile)

Max Activating Token Index: 446

Text #7

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7087. Min Act: -0.0000

Data Index: 721230 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7090. Min Act: -0.0000

Data Index: 861440 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1233007 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1226347 (The Pile)

Max Activating Token Index: 864

Text #11

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6984. Min Act: -0.0000

Data Index: 502678 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6497. Min Act: -0.0000

Data Index: 274932 (The Pile)

Max Activating Token Index: 614

Text #13

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1969958 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1525901 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6887. Min Act: -0.0000

Data Index: 662786 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1846943 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1235439 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5820. Min Act: -0.0000

Data Index: 13592 (The Pile)

Max Activating Token Index: 852

Text #19

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6579. Min Act: -0.0000

Data Index: 667304 (The Pile)

Max Activating Token Index: 278