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

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

Neuron 43 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7599. Min Act: -0.0000

Data Index: 111852 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.7587. Min Act: 0.0000

Data Index: 1420065 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6628. Min Act: -0.0000

Data Index: 531870 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.5399. Min Act: -0.0000

Data Index: 1504411 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.6795. Min Act: -0.0000

Data Index: 1498553 (Python Code)

Max Activating Token Index: 696

Text #5

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4670. Min Act: -0.0000

Data Index: 1539480 (Python Code)

Max Activating Token Index: 70

Text #6

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1499373 (Python Code)

Max Activating Token Index: 270

Text #7

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.3319. Min Act: -0.0000

Data Index: 996367 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1543437 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4300. Min Act: -0.0000

Data Index: 693393 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1447367 (Python Code)

Max Activating Token Index: 685

Text #11

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1639057 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4324. Min Act: -0.0000

Data Index: 666958 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4022. Min Act: -0.0000

Data Index: 587473 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.4068. Min Act: -0.0000

Data Index: 380670 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.3050. Min Act: -0.0000

Data Index: 561687 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.3975. Min Act: -0.0000

Data Index: 478171 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.3373. Min Act: -0.0000

Data Index: 117522 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.3252. Min Act: -0.0000

Data Index: 1573616 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 1.7599. Min Range: -1.7599

Max Act: 1.2796. Min Act: -0.0000

Data Index: 1425531 (Python Code)

Max Activating Token Index: 873