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

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

Neuron 2319 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: 1.1559. Min Range: -1.1559

Max Act: 1.0359. Min Act: -0.0002

Data Index: 309102 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 1.1559. Min Range: -1.1559

Max Act: 1.1559. Min Act: -0.0001

Data Index: 689151 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 1.1559. Min Range: -1.1559

Max Act: 1.0091. Min Act: -0.0002

Data Index: 304732 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.1559. Min Range: -1.1559

Max Act: 1.0350. Min Act: -0.0001

Data Index: 1142787 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 1.1559. Min Range: -1.1559

Max Act: 1.0351. Min Act: -0.0002

Data Index: 819969 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.8574. Min Act: -0.0001

Data Index: 391702 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9715. Min Act: -0.0002

Data Index: 1184754 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9768. Min Act: -0.0002

Data Index: 919417 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.8881. Min Act: -0.0002

Data Index: 87249 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.1559. Min Range: -1.1559

Max Act: 1.0561. Min Act: -0.0002

Data Index: 2861 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9765. Min Act: -0.0001

Data Index: 71726 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 1.1559. Min Range: -1.1559

Max Act: 1.0009. Min Act: -0.0002

Data Index: 104197 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9381. Min Act: -0.0001

Data Index: 365347 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9027. Min Act: -0.0002

Data Index: 138298 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9837. Min Act: -0.0001

Data Index: 611798 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9181. Min Act: -0.0002

Data Index: 1188843 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.8862. Min Act: -0.0002

Data Index: 1019416 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9650. Min Act: -0.0002

Data Index: 975088 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.9362. Min Act: -0.0001

Data Index: 628924 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.1559. Min Range: -1.1559

Max Act: 0.8431. Min Act: -0.0001

Data Index: 1143635 (C4 (Web Text))

Max Activating Token Index: 793