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

Dataset: The Pile

Neuron 946 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5906. Min Act: -0.0000

Data Index: 238286 (The Pile)

Max Activating Token Index: 515

Text #1

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1768318 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1272347 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1231350 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4574. Min Act: -0.0000

Data Index: 274596 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1479652 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4178. Min Act: 0.0000

Data Index: 1881354 (The Pile)

Max Activating Token Index: 905

Text #7

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1283758 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4244. Min Act: -0.0000

Data Index: 995846 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4134. Min Act: -0.0000

Data Index: 972172 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4121. Min Act: -0.0000

Data Index: 832581 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4062. Min Act: -0.0000

Data Index: 187760 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4054. Min Act: -0.0000

Data Index: 663524 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4041. Min Act: -0.0000

Data Index: 198347 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1820203 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1580176 (The Pile)

Max Activating Token Index: 761

Text #16

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1377327 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3970. Min Act: 0.0000

Data Index: 923515 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1268944 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.3921. Min Act: -0.0000

Data Index: 184112 (The Pile)

Max Activating Token Index: 116