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

Dataset: The Pile

Neuron 1629 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: 3.9927. Min Range: -3.9927

Max Act: 3.9927. Min Act: -0.0000

Data Index: 620076 (The Pile)

Max Activating Token Index: 274

Text #1

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.7781. Min Act: -0.0000

Data Index: 302955 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.7654. Min Act: -0.0000

Data Index: 226570 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.5983. Min Act: -0.0000

Data Index: 408348 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.1894. Min Act: -0.0000

Data Index: 246009 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.6429. Min Act: -0.0000

Data Index: 879425 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.3942. Min Act: -0.0000

Data Index: 666323 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.3969. Min Act: -0.0000

Data Index: 836059 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.2613. Min Act: -0.0000

Data Index: 774182 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.2082. Min Act: -0.0000

Data Index: 990380 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.1946. Min Act: -0.0000

Data Index: 1226657 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 3.9927. Min Range: -3.9927

Max Act: 2.9849. Min Act: -0.0000

Data Index: 1617505 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.1173. Min Act: -0.0000

Data Index: 799438 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 3.9927. Min Range: -3.9927

Max Act: 2.9185. Min Act: -0.0000

Data Index: 1270907 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.0398. Min Act: -0.0000

Data Index: 938875 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.0195. Min Act: -0.0000

Data Index: 507324 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.1620. Min Act: -0.0000

Data Index: 456923 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 3.9927. Min Range: -3.9927

Max Act: 2.8550. Min Act: -0.0000

Data Index: 497847 (The Pile)

Max Activating Token Index: 1013

Text #18

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.1604. Min Act: -0.0000

Data Index: 1500175 (The Pile)

Max Activating Token Index: 916

Text #19

Max Range: 3.9927. Min Range: -3.9927

Max Act: 2.9947. Min Act: -0.0000

Data Index: 1428226 (The Pile)

Max Activating Token Index: 321