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

Dataset: The Pile

Neuron 326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1994436 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1919546 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1448376 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2728. Min Act: -0.0000

Data Index: 887965 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2702. Min Act: -0.0000

Data Index: 668813 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1369774 (The Pile)

Max Activating Token Index: 511

Text #6

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1102024 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1721285 (The Pile)

Max Activating Token Index: 520

Text #8

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1295470 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1767783 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1090245 (The Pile)

Max Activating Token Index: 954

Text #11

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1028571 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1308127 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2157. Min Act: -0.0000

Data Index: 194543 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2033. Min Act: -0.0001

Data Index: 666671 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2073. Min Act: -0.0000

Data Index: 204377 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1378753 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1313816 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1493436 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 0.3132. Min Range: -0.3132

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1904249 (The Pile)

Max Activating Token Index: 359