Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3163 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1098818 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1995579 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2973. Min Act: -0.0000

Data Index: 597490 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1489356 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2677. Min Act: -0.0000

Data Index: 107672 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1494087 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2705. Min Act: -0.0000

Data Index: 201698 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2482. Min Act: -0.0000

Data Index: 914510 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2574. Min Act: -0.0000

Data Index: 623102 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1505219 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2674. Min Act: -0.0000

Data Index: 744890 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2437. Min Act: -0.0000

Data Index: 2192 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2263. Min Act: -0.0000

Data Index: 393804 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2204. Min Act: -0.0000

Data Index: 315384 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1014427 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1468476 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1046769 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2479. Min Act: -0.0000

Data Index: 1885273 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1910963 (The Pile)

Max Activating Token Index: 192

Text #19

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2254. Min Act: -0.0000

Data Index: 798410 (The Pile)

Max Activating Token Index: 267