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

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

Neuron 339 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0942. Min Range: -2.0942

Max Act: 2.0942. Min Act: -0.0000

Data Index: 29848 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.9365. Min Act: -0.0000

Data Index: 566753 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.8924. Min Act: -0.0000

Data Index: 464364 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.6961. Min Act: -0.0000

Data Index: 1072914 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.6680. Min Act: -0.0000

Data Index: 505183 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.6489. Min Act: -0.0000

Data Index: 1253789 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.6247. Min Act: -0.0000

Data Index: 1265896 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.5256. Min Act: -0.0000

Data Index: 634025 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.6731. Min Act: -0.0000

Data Index: 119814 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.6679. Min Act: -0.0000

Data Index: 1012507 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.6482. Min Act: -0.0000

Data Index: 466440 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.5796. Min Act: -0.0000

Data Index: 285225 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.4371. Min Act: -0.0000

Data Index: 637031 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.4780. Min Act: -0.0000

Data Index: 875210 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.4823. Min Act: -0.0000

Data Index: 953912 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.4853. Min Act: -0.0000

Data Index: 116603 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.4194. Min Act: -0.0000

Data Index: 1345120 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.4355. Min Act: -0.0000

Data Index: 266716 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.3811. Min Act: -0.0000

Data Index: 118631 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 2.0942. Min Range: -2.0942

Max Act: 1.3683. Min Act: -0.0000

Data Index: 316402 (C4 (Web Text))

Max Activating Token Index: 366