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

Dataset: The Pile

Neuron 802 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3390. Min Act: -0.0001

Data Index: 414334 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3375. Min Act: -0.0001

Data Index: 705361 (The Pile)

Max Activating Token Index: 542

Text #2

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3332. Min Act: -0.0001

Data Index: 1899902 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3286. Min Act: -0.0001

Data Index: 366896 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3223. Min Act: -0.0001

Data Index: 657852 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3130. Min Act: -0.0001

Data Index: 1200490 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2800. Min Act: -0.0001

Data Index: 1889028 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2931. Min Act: -0.0001

Data Index: 922196 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3016. Min Act: -0.0001

Data Index: 308193 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1878563 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2678. Min Act: -0.0001

Data Index: 605142 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1712331 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2913. Min Act: -0.0001

Data Index: 691329 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2966. Min Act: -0.0001

Data Index: 1964603 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1415637 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2925. Min Act: -0.0001

Data Index: 284138 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2723. Min Act: -0.0001

Data Index: 537974 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2909. Min Act: -0.0001

Data Index: 93651 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2767. Min Act: -0.0001

Data Index: 26011 (The Pile)

Max Activating Token Index: 72

Text #19

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2636. Min Act: -0.0001

Data Index: 123488 (The Pile)

Max Activating Token Index: 291