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

Dataset: The Pile

Neuron 649 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: 0.6458. Min Range: -0.6458

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1723228 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5975. Min Act: -0.0000

Data Index: 138187 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1921810 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1747465 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4650. Min Act: -0.0000

Data Index: 906008 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4225. Min Act: -0.0000

Data Index: 716302 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1513539 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1052073 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4524. Min Act: -0.0000

Data Index: 262696 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1710267 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1421858 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1260954 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1578393 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1306388 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1362935 (The Pile)

Max Activating Token Index: 994

Text #15

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1194759 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4320. Min Act: 0.0000

Data Index: 1190215 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1816752 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4257. Min Act: -0.0000

Data Index: 669188 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.6458. Min Range: -0.6458

Max Act: 0.4622. Min Act: -0.0000

Data Index: 40782 (The Pile)

Max Activating Token Index: 780