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

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

Neuron 1018 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.7547. Min Act: -0.0001

Data Index: 614317 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.7317. Min Act: -0.0001

Data Index: 1066255 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.5243. Min Act: -0.0001

Data Index: 620396 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.4134. Min Act: -0.0001

Data Index: 356118 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.4823. Min Act: -0.0001

Data Index: 1098844 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.5461. Min Act: -0.0001

Data Index: 1150955 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.3509. Min Act: -0.0001

Data Index: 543759 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.4346. Min Act: -0.0001

Data Index: 97167 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.5011. Min Act: -0.0001

Data Index: 976213 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.3972. Min Act: -0.0001

Data Index: 1189141 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.3933. Min Act: -0.0001

Data Index: 344685 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.4411. Min Act: -0.0001

Data Index: 930616 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.4009. Min Act: -0.0001

Data Index: 72850 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.0797. Min Act: -0.0001

Data Index: 327392 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.2899. Min Act: -0.0001

Data Index: 116330 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.4521. Min Act: -0.0001

Data Index: 888188 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.4128. Min Act: -0.0001

Data Index: 1235422 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.0922. Min Act: -0.0001

Data Index: 1171373 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.2717. Min Act: -0.0001

Data Index: 279268 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.7547. Min Range: -1.7547

Max Act: 1.1379. Min Act: -0.0001

Data Index: 62713 (C4 (Web Text))

Max Activating Token Index: 671