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

Dataset: The Pile

Neuron 4106 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: 0.6404. Min Range: -0.6404

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1562584 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1611113 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1012037 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5289. Min Act: -0.0000

Data Index: 452605 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5554. Min Act: -0.0000

Data Index: 405961 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1361300 (The Pile)

Max Activating Token Index: 798

Text #6

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4765. Min Act: -0.0000

Data Index: 232104 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1814671 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5161. Min Act: -0.0000

Data Index: 557325 (The Pile)

Max Activating Token Index: 447

Text #9

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1327008 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5179. Min Act: -0.0000

Data Index: 299955 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4999. Min Act: -0.0000

Data Index: 233656 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5054. Min Act: -0.0000

Data Index: 725436 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1780555 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4971. Min Act: -0.0000

Data Index: 811827 (The Pile)

Max Activating Token Index: 596

Text #15

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.5033. Min Act: -0.0000

Data Index: 872364 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4887. Min Act: -0.0000

Data Index: 194440 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1041817 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4642. Min Act: -0.0000

Data Index: 602608 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 0.6404. Min Range: -0.6404

Max Act: 0.4937. Min Act: -0.0000

Data Index: 153659 (The Pile)

Max Activating Token Index: 457