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

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

Neuron 1757 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: 0.4715. Min Range: -0.4715

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1621698 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1394662 (Python Code)

Max Activating Token Index: 514

Text #2

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1219254 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1456728 (Python Code)

Max Activating Token Index: 172

Text #4

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1315088 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1478379 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1637606 (Python Code)

Max Activating Token Index: 689

Text #7

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3908. Min Act: -0.0000

Data Index: 328815 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.4039. Min Act: -0.0000

Data Index: 329887 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1526394 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3672. Min Act: -0.0000

Data Index: 574022 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3900. Min Act: -0.0000

Data Index: 348732 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3737. Min Act: -0.0000

Data Index: 1588693 (Python Code)

Max Activating Token Index: 553

Text #13

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3742. Min Act: -0.0000

Data Index: 161866 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1191569 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3250. Min Act: 0.0000

Data Index: 1027027 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1181351 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1348270 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1042312 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.4715. Min Range: -0.4715

Max Act: 0.3617. Min Act: -0.0000

Data Index: 514959 (C4 (Web Text))

Max Activating Token Index: 106