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

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

Neuron 956 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0968. Min Range: -2.0968

Max Act: 2.0523. Min Act: -0.0000

Data Index: 467837 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 2.0968. Min Range: -2.0968

Max Act: 2.0078. Min Act: -0.0000

Data Index: 358868 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 2.0968. Min Range: -2.0968

Max Act: 2.0415. Min Act: -0.0000

Data Index: 61467 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.6886. Min Act: -0.0000

Data Index: 1009194 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 2.0968. Min Range: -2.0968

Max Act: 2.0968. Min Act: -0.0000

Data Index: 164573 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.8146. Min Act: -0.0000

Data Index: 26527 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.7850. Min Act: -0.0000

Data Index: 1322266 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.7707. Min Act: -0.0000

Data Index: 832582 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.7643. Min Act: -0.0000

Data Index: 795685 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.6298. Min Act: -0.0000

Data Index: 500639 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.8156. Min Act: -0.0000

Data Index: 941563 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.5634. Min Act: -0.0000

Data Index: 8574 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.5755. Min Act: -0.0000

Data Index: 110830 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.6452. Min Act: -0.0000

Data Index: 6104 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.6507. Min Act: -0.0000

Data Index: 294 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.7327. Min Act: -0.0000

Data Index: 353182 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.7308. Min Act: -0.0000

Data Index: 1023130 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.6436. Min Act: -0.0000

Data Index: 168804 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.6258. Min Act: -0.0000

Data Index: 1316898 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 2.0968. Min Range: -2.0968

Max Act: 1.6208. Min Act: -0.0000

Data Index: 104321 (C4 (Web Text))

Max Activating Token Index: 669