Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4597 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0001

Data Index: 533175 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1538473 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1381336 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1421281 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1581697 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1634755 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1013. Min Act: -0.0001

Data Index: 342383 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1016. Min Act: -0.0001

Data Index: 601581 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1001. Min Act: -0.0001

Data Index: 627925 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0969. Min Act: -0.0001

Data Index: 537867 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1531805 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0971. Min Act: -0.0001

Data Index: 754881 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0944. Min Act: -0.0001

Data Index: 363387 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0930. Min Act: -0.0001

Data Index: 483297 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1061980 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1115635 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0936. Min Act: -0.0001

Data Index: 57188 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1653879 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0933. Min Act: -0.0001

Data Index: 945236 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1627397 (Python Code)

Max Activating Token Index: 273