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

Dataset: The Pile

Neuron 958 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: 1.3515. Min Range: -1.3515

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1769677 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.1024. Min Act: -0.0000

Data Index: 1407196 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.1158. Min Act: -0.0000

Data Index: 77787 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 1.3515. Min Range: -1.3515

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1261069 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9928. Min Act: -0.0000

Data Index: 267677 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9650. Min Act: -0.0000

Data Index: 237319 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1724174 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1875923 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8273. Min Act: -0.0000

Data Index: 792241 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8589. Min Act: -0.0000

Data Index: 264594 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8349. Min Act: -0.0000

Data Index: 568422 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1044474 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8735. Min Act: -0.0000

Data Index: 325579 (The Pile)

Max Activating Token Index: 851

Text #13

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1375848 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8480. Min Act: -0.0000

Data Index: 772109 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8264. Min Act: -0.0000

Data Index: 569963 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8685. Min Act: -0.0000

Data Index: 916050 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8339. Min Act: -0.0000

Data Index: 739948 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1824463 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 1.3515. Min Range: -1.3515

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1397524 (The Pile)

Max Activating Token Index: 333