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

Dataset: The Pile

Neuron 1316 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.6494. Min Act: -0.0000

Data Index: 1411191 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4373. Min Act: -0.0000

Data Index: 1686908 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3969. Min Act: -0.0000

Data Index: 147786 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4093. Min Act: -0.0000

Data Index: 256627 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3641. Min Act: -0.0000

Data Index: 685804 (The Pile)

Max Activating Token Index: 196

Text #5

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3918. Min Act: -0.0000

Data Index: 807413 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3251. Min Act: -0.0000

Data Index: 794731 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2189. Min Act: -0.0000

Data Index: 204084 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3143. Min Act: -0.0000

Data Index: 1998053 (The Pile)

Max Activating Token Index: 122

Text #9

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3715. Min Act: -0.0000

Data Index: 490485 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1660127 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3296. Min Act: -0.0000

Data Index: 1613063 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3012. Min Act: -0.0000

Data Index: 536479 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2692. Min Act: -0.0000

Data Index: 644285 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1819185 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1132302 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2981. Min Act: -0.0000

Data Index: 744236 (The Pile)

Max Activating Token Index: 260

Text #17

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1410195 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2194. Min Act: -0.0000

Data Index: 609453 (The Pile)

Max Activating Token Index: 451

Text #19

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1841271 (The Pile)

Max Activating Token Index: 451