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

Dataset: The Pile

Neuron 2084 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: 4.4104. Min Range: -4.4104

Max Act: 4.0642. Min Act: -0.0000

Data Index: 965585 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.4104. Min Act: -0.0000

Data Index: 840135 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.3876. Min Act: -0.0000

Data Index: 1706180 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.0525. Min Act: -0.0000

Data Index: 1731034 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.2961. Min Act: -0.0000

Data Index: 1594786 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.1165. Min Act: -0.0000

Data Index: 1656013 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.8942. Min Act: -0.0000

Data Index: 1488239 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.2176. Min Act: -0.0000

Data Index: 1060010 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.6866. Min Act: -0.0000

Data Index: 201774 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.3086. Min Act: -0.0000

Data Index: 4979 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.8127. Min Act: -0.0000

Data Index: 1498468 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.4643. Min Act: -0.0000

Data Index: 553614 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 4.4104. Min Range: -4.4104

Max Act: 4.1014. Min Act: -0.0000

Data Index: 1249302 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.7050. Min Act: -0.0000

Data Index: 1027808 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.7168. Min Act: -0.0000

Data Index: 1186588 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.8648. Min Act: -0.0000

Data Index: 850888 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.3046. Min Act: -0.0000

Data Index: 1669102 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.8180. Min Act: -0.0000

Data Index: 209940 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.7606. Min Act: -0.0000

Data Index: 1645064 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 4.4104. Min Range: -4.4104

Max Act: 3.4839. Min Act: -0.0000

Data Index: 1954458 (The Pile)

Max Activating Token Index: 189