Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2524 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1541569 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1319670 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4689. Min Act: -0.0000

Data Index: 465243 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4678. Min Act: -0.0000

Data Index: 823631 (The Pile)

Max Activating Token Index: 321

Text #4

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4668. Min Act: -0.0001

Data Index: 1673496 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4403. Min Act: -0.0000

Data Index: 905368 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4537. Min Act: -0.0001

Data Index: 1440858 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4482. Min Act: -0.0000

Data Index: 702814 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4467. Min Act: -0.0000

Data Index: 783278 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4458. Min Act: -0.0000

Data Index: 982378 (The Pile)

Max Activating Token Index: 109

Text #10

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4430. Min Act: -0.0001

Data Index: 1231480 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4497. Min Act: -0.0000

Data Index: 860682 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1281544 (The Pile)

Max Activating Token Index: 39

Text #13

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4390. Min Act: -0.0000

Data Index: 91885 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4270. Min Act: -0.0000

Data Index: 353077 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1997252 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1509960 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1101895 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3975. Min Act: -0.0000

Data Index: 846487 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3831. Min Act: -0.0000

Data Index: 772827 (The Pile)

Max Activating Token Index: 161