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

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

Neuron 4769 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: 0.1835. Min Range: -0.1835

Max Act: 0.1835. Min Act: -0.0001

Data Index: 916174 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1062544 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1098. Min Act: -0.0001

Data Index: 366213 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1058. Min Act: -0.0001

Data Index: 543015 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1141. Min Act: -0.0001

Data Index: 904075 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0927. Min Act: -0.0001

Data Index: 967156 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1186095 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0960. Min Act: -0.0001

Data Index: 383146 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0743. Min Act: -0.0001

Data Index: 827398 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0858. Min Act: -0.0001

Data Index: 484991 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1560036 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0739. Min Act: -0.0001

Data Index: 234870 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1378379 (Python Code)

Max Activating Token Index: 405

Text #13

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1343076 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1396264 (Python Code)

Max Activating Token Index: 441

Text #15

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0811. Min Act: -0.0001

Data Index: 302023 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0723. Min Act: -0.0001

Data Index: 18158 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0801. Min Act: -0.0001

Data Index: 659581 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1433487 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1507286 (Python Code)

Max Activating Token Index: 521