Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 320 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2861. Min Range: -3.2861

Max Act: 3.2861. Min Act: -0.0000

Data Index: 162877 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 3.2861. Min Range: -3.2861

Max Act: 3.0342. Min Act: -0.0000

Data Index: 751763 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 3.2861. Min Range: -3.2861

Max Act: 2.6109. Min Act: -0.0000

Data Index: 991523 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 3.2861. Min Range: -3.2861

Max Act: 2.1320. Min Act: -0.0000

Data Index: 1021152 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 3.2861. Min Range: -3.2861

Max Act: 2.4655. Min Act: -0.0000

Data Index: 1060037 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 3.2861. Min Range: -3.2861

Max Act: 2.0727. Min Act: -0.0000

Data Index: 195408 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.8610. Min Act: -0.0000

Data Index: 630986 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 3.2861. Min Range: -3.2861

Max Act: 2.2437. Min Act: -0.0000

Data Index: 1375117 (Python Code)

Max Activating Token Index: 960

Text #8

Max Range: 3.2861. Min Range: -3.2861

Max Act: 2.1751. Min Act: -0.0000

Data Index: 218371 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.9057. Min Act: -0.0000

Data Index: 905298 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.8537. Min Act: -0.0000

Data Index: 783486 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.8618. Min Act: -0.0000

Data Index: 440287 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.8369. Min Act: -0.0000

Data Index: 1014417 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.7484. Min Act: -0.0000

Data Index: 798525 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.4772. Min Act: -0.0000

Data Index: 1282388 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1372184 (Python Code)

Max Activating Token Index: 775

Text #16

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.8336. Min Act: -0.0000

Data Index: 88312 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.6081. Min Act: -0.0000

Data Index: 642744 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.6771. Min Act: -0.0000

Data Index: 689530 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 3.2861. Min Range: -3.2861

Max Act: 1.4040. Min Act: -0.0000

Data Index: 1074304 (C4 (Web Text))

Max Activating Token Index: 330