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

Dataset: The Pile

Neuron 3208 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1540273 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4316. Min Act: -0.0000

Data Index: 862647 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1543366 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4341. Min Act: -0.0000

Data Index: 906144 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1767494 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1370217 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3785. Min Act: -0.0000

Data Index: 524777 (The Pile)

Max Activating Token Index: 237

Text #7

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3773. Min Act: -0.0000

Data Index: 140523 (The Pile)

Max Activating Token Index: 565

Text #8

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3650. Min Act: -0.0000

Data Index: 990117 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3498. Min Act: -0.0000

Data Index: 68088 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3589. Min Act: -0.0000

Data Index: 106755 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1820343 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1189182 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3320. Min Act: -0.0000

Data Index: 709614 (The Pile)

Max Activating Token Index: 927

Text #14

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1729927 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1792432 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1766636 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1386557 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3433. Min Act: -0.0000

Data Index: 963266 (The Pile)

Max Activating Token Index: 64

Text #19

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.3315. Min Act: -0.0000

Data Index: 41314 (The Pile)

Max Activating Token Index: 692