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

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

Neuron 4548 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8612. Min Range: -3.8612

Max Act: 3.8612. Min Act: -0.0000

Data Index: 988502 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.8286. Min Act: -0.0000

Data Index: 954002 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.9235. Min Act: -0.0000

Data Index: 856621 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.8064. Min Act: -0.0000

Data Index: 718886 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.9176. Min Act: -0.0000

Data Index: 861560 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.5064. Min Act: -0.0000

Data Index: 419693 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.5660. Min Act: -0.0000

Data Index: 895043 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.6925. Min Act: -0.0000

Data Index: 472553 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.7756. Min Act: -0.0000

Data Index: 915400 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.7101. Min Act: -0.0000

Data Index: 774435 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.5521. Min Act: -0.0000

Data Index: 262870 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.3682. Min Act: -0.0000

Data Index: 171056 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.5013. Min Act: -0.0000

Data Index: 865086 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.6412. Min Act: -0.0000

Data Index: 262928 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.6177. Min Act: -0.0000

Data Index: 47842 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.3128. Min Act: -0.0000

Data Index: 504635 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.4168. Min Act: -0.0000

Data Index: 50058 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.1951. Min Act: -0.0000

Data Index: 13447 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.4491. Min Act: -0.0000

Data Index: 16352 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 3.8612. Min Range: -3.8612

Max Act: 2.6239. Min Act: -0.0000

Data Index: 760949 (C4 (Web Text))

Max Activating Token Index: 927