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

Dataset: The Pile

Neuron 3022 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: 0.5298. Min Range: -0.5298

Max Act: 0.5298. Min Act: -0.0000

Data Index: 555774 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1989529 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4706. Min Act: -0.0001

Data Index: 1720127 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1659454 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4612. Min Act: -0.0000

Data Index: 440922 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4463. Min Act: -0.0000

Data Index: 847125 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1800021 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4334. Min Act: -0.0000

Data Index: 988346 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3882. Min Act: -0.0000

Data Index: 521117 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4197. Min Act: -0.0000

Data Index: 410317 (The Pile)

Max Activating Token Index: 842

Text #10

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1788206 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4179. Min Act: -0.0000

Data Index: 554083 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1481674 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1390742 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4224. Min Act: -0.0000

Data Index: 51945 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.4080. Min Act: -0.0000

Data Index: 461156 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3803. Min Act: -0.0001

Data Index: 824797 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1035956 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3735. Min Act: -0.0001

Data Index: 700249 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 0.5298. Min Range: -0.5298

Max Act: 0.3983. Min Act: -0.0000

Data Index: 365069 (The Pile)

Max Activating Token Index: 690