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

Dataset: The Pile

Neuron 527 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: 1.7888. Min Range: -1.7888

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1404454 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3304. Min Act: -0.0000

Data Index: 66378 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2679. Min Act: -0.0000

Data Index: 1744159 (The Pile)

Max Activating Token Index: 557

Text #3

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3034. Min Act: -0.0000

Data Index: 939207 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.2215. Min Act: -0.0000

Data Index: 1995446 (The Pile)

Max Activating Token Index: 287

Text #5

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1870. Min Act: -0.0000

Data Index: 810139 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1761. Min Act: -0.0000

Data Index: 202256 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1881. Min Act: -0.0000

Data Index: 66022 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1260246 (The Pile)

Max Activating Token Index: 912

Text #9

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1842216 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1185. Min Act: -0.0000

Data Index: 1179431 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1348004 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1218702 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0096. Min Act: -0.0000

Data Index: 576978 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0197. Min Act: -0.0000

Data Index: 917935 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0166. Min Act: -0.0000

Data Index: 96843 (The Pile)

Max Activating Token Index: 532

Text #16

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1918885 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1782337 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 1.7888. Min Range: -1.7888

Max Act: 1.0344. Min Act: -0.0000

Data Index: 528258 (The Pile)

Max Activating Token Index: 840

Text #19

Max Range: 1.7888. Min Range: -1.7888

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1145938 (The Pile)

Max Activating Token Index: 910