Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5739 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2983. Min Range: -1.2983

Max Act: 1.2983. Min Act: -0.0000

Data Index: 19480 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.2983. Min Range: -1.2983

Max Act: 1.0262. Min Act: -0.0000

Data Index: 199934 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.9912. Min Act: -0.0000

Data Index: 902262 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.2983. Min Range: -1.2983

Max Act: 1.0454. Min Act: -0.0000

Data Index: 757453 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.2983. Min Range: -1.2983

Max Act: 1.0089. Min Act: -0.0000

Data Index: 334184 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 1.2983. Min Range: -1.2983

Max Act: 1.0370. Min Act: -0.0000

Data Index: 320250 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 1.2983. Min Range: -1.2983

Max Act: 1.0643. Min Act: -0.0000

Data Index: 681147 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1271673 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1332082 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.9028. Min Act: -0.0000

Data Index: 488538 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1204019 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.9247. Min Act: -0.0000

Data Index: 120845 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.8931. Min Act: -0.0000

Data Index: 472890 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.8571. Min Act: -0.0000

Data Index: 509819 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1200644 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.8018. Min Act: -0.0000

Data Index: 770529 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.8841. Min Act: -0.0000

Data Index: 564834 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.8065. Min Act: -0.0000

Data Index: 567300 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.7504. Min Act: -0.0000

Data Index: 1558205 (Python Code)

Max Activating Token Index: 545

Text #19

Max Range: 1.2983. Min Range: -1.2983

Max Act: 0.7267. Min Act: -0.0000

Data Index: 847232 (C4 (Web Text))

Max Activating Token Index: 120