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

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

Neuron 3235 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1580226 (Python Code)

Max Activating Token Index: 739

Text #1

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1390851 (Python Code)

Max Activating Token Index: 219

Text #2

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1461018 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1308056 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1437107 (Python Code)

Max Activating Token Index: 99

Text #5

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6753. Min Act: -0.0000

Data Index: 800525 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1523740 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1363372 (Python Code)

Max Activating Token Index: 684

Text #8

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1029981 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1379731 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1271731 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6496. Min Act: -0.0000

Data Index: 622030 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1577198 (Python Code)

Max Activating Token Index: 350

Text #13

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6073. Min Act: -0.0000

Data Index: 156242 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1078022 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1524000 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1505543 (Python Code)

Max Activating Token Index: 942

Text #17

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1459563 (Python Code)

Max Activating Token Index: 884

Text #18

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5984. Min Act: -0.0000

Data Index: 259018 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.7584. Min Range: -0.7584

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1412744 (Python Code)

Max Activating Token Index: 975