Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1375 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4531. Min Act: -0.0001

Data Index: 6196 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.4711. Min Act: -0.0001

Data Index: 1476759 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3990. Min Act: -0.0001

Data Index: 1356338 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3640. Min Act: -0.0001

Data Index: 1493024 (Python Code)

Max Activating Token Index: 407

Text #4

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3529. Min Act: -0.0001

Data Index: 947266 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3451. Min Act: -0.0001

Data Index: 571334 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3313. Min Act: -0.0001

Data Index: 1112574 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1640161 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3085. Min Act: -0.0001

Data Index: 801656 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3311. Min Act: -0.0001

Data Index: 970169 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3101. Min Act: -0.0001

Data Index: 599970 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3300. Min Act: -0.0001

Data Index: 844176 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3237. Min Act: -0.0001

Data Index: 1005721 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3087. Min Act: -0.0001

Data Index: 632048 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3030. Min Act: -0.0001

Data Index: 56133 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.2881. Min Act: -0.0001

Data Index: 36508 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.2877. Min Act: -0.0001

Data Index: 737083 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.2996. Min Act: -0.0001

Data Index: 132316 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.3102. Min Act: -0.0001

Data Index: 1466918 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 0.4711. Min Range: -0.4711

Max Act: 0.2834. Min Act: -0.0001

Data Index: 115572 (C4 (Web Text))

Max Activating Token Index: 547