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

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

Neuron 3227 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.8127. Min Act: -0.0001

Data Index: 594081 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7965. Min Act: -0.0001

Data Index: 833223 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7997. Min Act: -0.0001

Data Index: 236068 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7169. Min Act: -0.0001

Data Index: 337735 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7996. Min Act: -0.0001

Data Index: 743292 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7587. Min Act: -0.0001

Data Index: 168277 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.8499. Min Act: -0.0001

Data Index: 1176169 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7565. Min Act: -0.0001

Data Index: 330622 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7471. Min Act: -0.0001

Data Index: 272668 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7862. Min Act: -0.0001

Data Index: 152298 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6007. Min Act: -0.0001

Data Index: 736608 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.8205. Min Act: -0.0001

Data Index: 1138316 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7014. Min Act: -0.0001

Data Index: 323149 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6738. Min Act: -0.0001

Data Index: 964364 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6490. Min Act: -0.0001

Data Index: 1233800 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7439. Min Act: -0.0001

Data Index: 883417 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.7397. Min Act: -0.0001

Data Index: 290376 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.5210. Min Act: -0.0001

Data Index: 460408 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6860. Min Act: -0.0001

Data Index: 1182886 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.8499. Min Range: -1.8499

Max Act: 1.6294. Min Act: -0.0001

Data Index: 1112856 (C4 (Web Text))

Max Activating Token Index: 37