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

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

Neuron 4368 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1076. Min Range: -1.1076

Max Act: 1.1076. Min Act: -0.0001

Data Index: 43904 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.8572. Min Act: -0.0001

Data Index: 542398 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.7986. Min Act: -0.0001

Data Index: 956963 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.7323. Min Act: -0.0001

Data Index: 730121 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.7137. Min Act: -0.0001

Data Index: 70373 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6743. Min Act: -0.0001

Data Index: 272919 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6912. Min Act: -0.0001

Data Index: 1091438 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.7112. Min Act: -0.0001

Data Index: 723511 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.7086. Min Act: -0.0001

Data Index: 897833 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6850. Min Act: -0.0001

Data Index: 898442 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6931. Min Act: -0.0001

Data Index: 406133 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6509. Min Act: -0.0001

Data Index: 157619 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6628. Min Act: -0.0001

Data Index: 859122 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6596. Min Act: -0.0001

Data Index: 667656 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6593. Min Act: -0.0001

Data Index: 636146 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6932. Min Act: -0.0001

Data Index: 1235761 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6491. Min Act: -0.0001

Data Index: 703286 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6424. Min Act: -0.0001

Data Index: 396331 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.6420. Min Act: -0.0001

Data Index: 615491 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.1076. Min Range: -1.1076

Max Act: 0.7249. Min Act: -0.0001

Data Index: 1281614 (C4 (Web Text))

Max Activating Token Index: 193