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

Dataset: The Pile

Neuron 3810 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: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0000

Data Index: 863100 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1163. Min Act: -0.0000

Data Index: 467209 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1253018 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1536250 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1270977 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1657852 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1832631 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1432584 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1097. Min Act: -0.0000

Data Index: 238214 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0934. Min Act: -0.0000

Data Index: 1128821 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1721181 (The Pile)

Max Activating Token Index: 772

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0851. Min Act: -0.0000

Data Index: 738636 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0977. Min Act: -0.0000

Data Index: 196823 (The Pile)

Max Activating Token Index: 418

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0947. Min Act: -0.0000

Data Index: 912208 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1736222 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0952. Min Act: -0.0000

Data Index: 805592 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0973. Min Act: -0.0000

Data Index: 423627 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0902. Min Act: -0.0000

Data Index: 220883 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1588166 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1582162 (The Pile)

Max Activating Token Index: 688