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

Dataset: The Pile

Neuron 3778 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: 0.8394. Min Range: -0.8394

Max Act: 0.8053. Min Act: -0.0000

Data Index: 162422 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1719563 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5613. Min Act: -0.0000

Data Index: 903963 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6163. Min Act: -0.0000

Data Index: 603593 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6397. Min Act: -0.0000

Data Index: 255014 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1160324 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5892. Min Act: -0.0000

Data Index: 656272 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5899. Min Act: -0.0000

Data Index: 888099 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1865793 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1199269 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5326. Min Act: -0.0000

Data Index: 514552 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1081880 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1084978 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1993378 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1828049 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5248. Min Act: -0.0000

Data Index: 661030 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5164. Min Act: -0.0000

Data Index: 481588 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5119. Min Act: -0.0000

Data Index: 722580 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.5293. Min Act: -0.0000

Data Index: 494633 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 0.8394. Min Range: -0.8394

Max Act: 0.4745. Min Act: -0.0000

Data Index: 222583 (The Pile)

Max Activating Token Index: 356