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

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

Neuron 315 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3301. Min Act: -0.0003

Data Index: 608324 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3328. Min Act: -0.0003

Data Index: 593270 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3291. Min Act: -0.0003

Data Index: 350677 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3120. Min Act: -0.0003

Data Index: 1308470 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3113. Min Act: -0.0003

Data Index: 873730 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2975. Min Act: -0.0003

Data Index: 807033 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.3082. Min Act: -0.0003

Data Index: 298787 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2739. Min Act: -0.0003

Data Index: 324440 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2933. Min Act: -0.0003

Data Index: 926860 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2873. Min Act: -0.0003

Data Index: 701539 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2716. Min Act: -0.0003

Data Index: 418977 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2547. Min Act: -0.0003

Data Index: 1150532 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2823. Min Act: -0.0003

Data Index: 943285 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2631. Min Act: -0.0004

Data Index: 1228536 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2699. Min Act: -0.0003

Data Index: 675288 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2903. Min Act: -0.0003

Data Index: 1030402 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2742. Min Act: -0.0003

Data Index: 334261 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2797. Min Act: -0.0003

Data Index: 1269527 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2786. Min Act: -0.0003

Data Index: 688853 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.3328. Min Range: -0.3328

Max Act: 0.2581. Min Act: -0.0003

Data Index: 1272432 (C4 (Web Text))

Max Activating Token Index: 1004