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

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

Neuron 173 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: 2.0689. Min Range: -2.0689

Max Act: 2.0689. Min Act: -0.0000

Data Index: 1147103 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.7487. Min Act: -0.0000

Data Index: 114532 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.7371. Min Act: -0.0000

Data Index: 1305647 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.7035. Min Act: -0.0000

Data Index: 1497952 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.6001. Min Act: -0.0000

Data Index: 1132325 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.6050. Min Act: -0.0000

Data Index: 262738 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.5823. Min Act: -0.0000

Data Index: 654507 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.4716. Min Act: -0.0000

Data Index: 41291 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.6576. Min Act: -0.0000

Data Index: 1015467 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1357435 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.5297. Min Act: -0.0000

Data Index: 155977 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.3692. Min Act: -0.0000

Data Index: 520973 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.5436. Min Act: -0.0000

Data Index: 370875 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.3458. Min Act: -0.0000

Data Index: 777416 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.3004. Min Act: -0.0000

Data Index: 383544 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.5404. Min Act: -0.0000

Data Index: 1157502 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.2605. Min Act: -0.0000

Data Index: 183052 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.2545. Min Act: -0.0000

Data Index: 702818 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.2736. Min Act: -0.0000

Data Index: 312447 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 2.0689. Min Range: -2.0689

Max Act: 1.3343. Min Act: -0.0000

Data Index: 1543168 (Python Code)

Max Activating Token Index: 36