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

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

Neuron 3213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.3647. Min Act: -0.0000

Data Index: 162364 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1399. Min Act: -0.0000

Data Index: 185943 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1070. Min Act: -0.0000

Data Index: 545088 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1012863 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8496. Min Act: -0.0000

Data Index: 343061 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1176819 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8430. Min Act: -0.0000

Data Index: 465818 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8099. Min Act: -0.0000

Data Index: 459021 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7936. Min Act: -0.0000

Data Index: 807703 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1643891 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1437456 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1656167 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1136797 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1485492 (Python Code)

Max Activating Token Index: 190

Text #14

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1447856 (Python Code)

Max Activating Token Index: 892

Text #15

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1133174 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1430132 (Python Code)

Max Activating Token Index: 626

Text #17

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1534527 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1528829 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1471271 (Python Code)

Max Activating Token Index: 53