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

Dataset: The Pile

Neuron 4386 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: 0.5593. Min Range: -0.5593

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1120718 (The Pile)

Max Activating Token Index: 794

Text #1

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5593. Min Act: -0.0000

Data Index: 771198 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5037. Min Act: -0.0000

Data Index: 686956 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1356374 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3937. Min Act: -0.0000

Data Index: 153443 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1758256 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4452. Min Act: -0.0000

Data Index: 658183 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4004. Min Act: -0.0000

Data Index: 652255 (The Pile)

Max Activating Token Index: 671

Text #8

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1739151 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1421936 (The Pile)

Max Activating Token Index: 347

Text #10

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3645. Min Act: -0.0000

Data Index: 90691 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3509. Min Act: -0.0000

Data Index: 914554 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3296. Min Act: -0.0000

Data Index: 445033 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1767913 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1866464 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1772099 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1544910 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3639. Min Act: -0.0000

Data Index: 998515 (The Pile)

Max Activating Token Index: 544

Text #18

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3749. Min Act: -0.0000

Data Index: 476486 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1201606 (The Pile)

Max Activating Token Index: 279