Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 563 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4247. Min Range: -2.4247

Max Act: 2.4247. Min Act: -0.0000

Data Index: 713682 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 2.4247. Min Range: -2.4247

Max Act: 2.2596. Min Act: -0.0000

Data Index: 1259246 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 2.4247. Min Range: -2.4247

Max Act: 2.0301. Min Act: -0.0000

Data Index: 461663 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 2.4247. Min Range: -2.4247

Max Act: 2.0559. Min Act: -0.0000

Data Index: 204631 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.8200. Min Act: -0.0000

Data Index: 491613 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.8017. Min Act: -0.0000

Data Index: 638979 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.5599. Min Act: -0.0000

Data Index: 1162770 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.6321. Min Act: -0.0000

Data Index: 614068 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1177460 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.5940. Min Act: -0.0000

Data Index: 412798 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4971. Min Act: -0.0000

Data Index: 292908 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4450. Min Act: -0.0000

Data Index: 414099 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.3336. Min Act: -0.0000

Data Index: 840211 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4240. Min Act: -0.0000

Data Index: 1186447 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4954. Min Act: -0.0000

Data Index: 121381 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.5793. Min Act: -0.0000

Data Index: 1192946 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4607. Min Act: -0.0000

Data Index: 746815 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4194. Min Act: -0.0000

Data Index: 940870 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4262. Min Act: -0.0000

Data Index: 192353 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 2.4247. Min Range: -2.4247

Max Act: 1.4030. Min Act: -0.0000

Data Index: 1096109 (C4 (Web Text))

Max Activating Token Index: 920