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

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

Neuron 647 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.7715. Min Act: -0.0000

Data Index: 1569795 (Python Code)

Max Activating Token Index: 183

Text #1

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.8127. Min Act: -0.0001

Data Index: 1364839 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.5061. Min Act: -0.0001

Data Index: 1444584 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.3933. Min Act: -0.0001

Data Index: 1465729 (Python Code)

Max Activating Token Index: 166

Text #4

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1786. Min Act: 0.0000

Data Index: 158876 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1463231 (Python Code)

Max Activating Token Index: 825

Text #6

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1527199 (Python Code)

Max Activating Token Index: 628

Text #7

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.0128. Min Act: -0.0000

Data Index: 1465949 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1436102 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1532148 (Python Code)

Max Activating Token Index: 759

Text #10

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1452190 (Python Code)

Max Activating Token Index: 913

Text #11

Max Range: 1.8127. Min Range: -1.8127

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1530885 (Python Code)

Max Activating Token Index: 865

Text #12

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.9258. Min Act: -0.0001

Data Index: 1400539 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.9737. Min Act: -0.0000

Data Index: 775067 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.8695. Min Act: -0.0000

Data Index: 705527 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1612577 (Python Code)

Max Activating Token Index: 407

Text #16

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.8474. Min Act: 0.0000

Data Index: 669436 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.9365. Min Act: 0.0000

Data Index: 824027 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1379837 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 1.8127. Min Range: -1.8127

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1507718 (Python Code)

Max Activating Token Index: 923