Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.7456. Min Act: -0.0001

Data Index: 762112 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.4453. Min Act: -0.0002

Data Index: 199072 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.4354. Min Act: -0.0002

Data Index: 439520 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1566. Min Act: -0.0002

Data Index: 535335 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.3904. Min Act: -0.0002

Data Index: 1082580 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.3823. Min Act: -0.0001

Data Index: 972929 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.3597. Min Act: -0.0002

Data Index: 1029779 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.3101. Min Act: -0.0002

Data Index: 1033354 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1964. Min Act: -0.0001

Data Index: 1115856 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1695. Min Act: -0.0001

Data Index: 938369 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.2036. Min Act: -0.0001

Data Index: 524315 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1096. Min Act: -0.0001

Data Index: 488164 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1574. Min Act: -0.0002

Data Index: 485628 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.0978. Min Act: -0.0001

Data Index: 1191 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1935. Min Act: -0.0002

Data Index: 395370 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1119. Min Act: -0.0001

Data Index: 589242 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1715. Min Act: -0.0002

Data Index: 988804 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1017. Min Act: -0.0002

Data Index: 1165223 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.0941. Min Act: -0.0002

Data Index: 591843 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 1.7456. Min Range: -1.7456

Max Act: 1.1609. Min Act: -0.0002

Data Index: 104104 (C4 (Web Text))

Max Activating Token Index: 531