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

Dataset: The Pile

Neuron 4113 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: 1.5508. Min Range: -1.5508

Max Act: 1.5508. Min Act: -0.0000

Data Index: 57440 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.5352. Min Act: -0.0000

Data Index: 704114 (The Pile)

Max Activating Token Index: 913

Text #2

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.3169. Min Act: -0.0000

Data Index: 645914 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.3080. Min Act: -0.0000

Data Index: 789205 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.3147. Min Act: -0.0000

Data Index: 1644765 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.3069. Min Act: -0.0000

Data Index: 36457 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1786636 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.3003. Min Act: -0.0000

Data Index: 688603 (The Pile)

Max Activating Token Index: 574

Text #8

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2916. Min Act: -0.0000

Data Index: 898288 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2150. Min Act: -0.0000

Data Index: 1897528 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2748. Min Act: -0.0000

Data Index: 255056 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2703. Min Act: -0.0000

Data Index: 519652 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1042089 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2606. Min Act: -0.0000

Data Index: 15393 (The Pile)

Max Activating Token Index: 204

Text #14

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2496. Min Act: -0.0000

Data Index: 945698 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1093007 (The Pile)

Max Activating Token Index: 216

Text #16

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1086295 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2206. Min Act: -0.0000

Data Index: 473878 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1426844 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 1.5508. Min Range: -1.5508

Max Act: 1.2904. Min Act: -0.0000

Data Index: 1154876 (The Pile)

Max Activating Token Index: 551