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

Dataset: The Pile

Neuron 2723 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1199. Min Range: -5.1199

Max Act: 5.1199. Min Act: -0.0000

Data Index: 646117 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 5.1199. Min Range: -5.1199

Max Act: 4.3887. Min Act: -0.0000

Data Index: 1927365 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.9546. Min Act: -0.0000

Data Index: 1739236 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.6567. Min Act: -0.0000

Data Index: 1191873 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.7854. Min Act: -0.0000

Data Index: 645879 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.6411. Min Act: -0.0000

Data Index: 850306 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.5752. Min Act: -0.0000

Data Index: 935849 (The Pile)

Max Activating Token Index: 671

Text #7

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.7060. Min Act: -0.0000

Data Index: 711109 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.5340. Min Act: -0.0000

Data Index: 480201 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.7996. Min Act: -0.0000

Data Index: 705978 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.3064. Min Act: -0.0000

Data Index: 767318 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.4174. Min Act: -0.0000

Data Index: 1945319 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.2533. Min Act: -0.0000

Data Index: 450500 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.5442. Min Act: -0.0000

Data Index: 1966848 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.3420. Min Act: -0.0000

Data Index: 4529 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.1280. Min Act: -0.0000

Data Index: 92436 (The Pile)

Max Activating Token Index: 438

Text #16

Max Range: 5.1199. Min Range: -5.1199

Max Act: 2.9388. Min Act: -0.0000

Data Index: 1302831 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 5.1199. Min Range: -5.1199

Max Act: 2.8527. Min Act: -0.0000

Data Index: 1540024 (The Pile)

Max Activating Token Index: 624

Text #18

Max Range: 5.1199. Min Range: -5.1199

Max Act: 3.0001. Min Act: -0.0000

Data Index: 879254 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 5.1199. Min Range: -5.1199

Max Act: 2.9669. Min Act: -0.0000

Data Index: 829097 (The Pile)

Max Activating Token Index: 580