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

Dataset: The Pile

Neuron 2060 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.8562. Min Act: -0.0000

Data Index: 1635848 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6156. Min Act: -0.0000

Data Index: 86274 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1552886 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1966516 (The Pile)

Max Activating Token Index: 601

Text #4

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1008061 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.5645. Min Act: -0.0000

Data Index: 137361 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.5034. Min Act: -0.0000

Data Index: 324783 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4902. Min Act: -0.0000

Data Index: 1567187 (The Pile)

Max Activating Token Index: 944

Text #8

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4409. Min Act: -0.0000

Data Index: 417673 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.5259. Min Act: -0.0000

Data Index: 102138 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1952583 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4918. Min Act: -0.0000

Data Index: 952091 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.5254. Min Act: -0.0000

Data Index: 532320 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1499286 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.5155. Min Act: -0.0000

Data Index: 87472 (The Pile)

Max Activating Token Index: 338

Text #15

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1928440 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4713. Min Act: -0.0000

Data Index: 460143 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1618702 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1054101 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 0.8562. Min Range: -0.8562

Max Act: 0.4671. Min Act: -0.0000

Data Index: 339902 (The Pile)

Max Activating Token Index: 465