Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1427 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.5137. Min Act: -0.0000

Data Index: 960280 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1764418 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4952. Min Act: -0.0000

Data Index: 617541 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1842891 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3900. Min Act: -0.0000

Data Index: 1844615 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4299. Min Act: -0.0000

Data Index: 1796236 (The Pile)

Max Activating Token Index: 906

Text #6

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3841. Min Act: -0.0000

Data Index: 5677 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4222. Min Act: -0.0000

Data Index: 30067 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3959. Min Act: -0.0000

Data Index: 171926 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3677. Min Act: -0.0000

Data Index: 158833 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3956. Min Act: -0.0000

Data Index: 200189 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1533383 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1036063 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3698. Min Act: -0.0000

Data Index: 264527 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1222865 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1104977 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1602614 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3570. Min Act: 0.0000

Data Index: 790369 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1316725 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3458. Min Act: -0.0000

Data Index: 257188 (The Pile)

Max Activating Token Index: 394