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

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

Neuron 680 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: 0.4815. Min Range: -0.4815

Max Act: 0.4815. Min Act: -0.0000

Data Index: 789919 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.4567. Min Act: -0.0000

Data Index: 322997 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3832. Min Act: -0.0000

Data Index: 571087 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.3622. Min Act: -0.0000

Data Index: 165310 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2791. Min Act: -0.0000

Data Index: 551852 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2522. Min Act: -0.0000

Data Index: 341246 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1569399 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1367960 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1324844 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1407105 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1996. Min Act: -0.0000

Data Index: 430153 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1935. Min Act: -0.0000

Data Index: 848222 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.2409. Min Act: -0.0000

Data Index: 180380 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1410419 (Python Code)

Max Activating Token Index: 455

Text #14

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1958. Min Act: -0.0000

Data Index: 58901 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1139618 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1741. Min Act: 0.0000

Data Index: 446835 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1798. Min Act: -0.0000

Data Index: 921428 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1726. Min Act: -0.0000

Data Index: 586967 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.4815. Min Range: -0.4815

Max Act: 0.1700. Min Act: -0.0000

Data Index: 215764 (C4 (Web Text))

Max Activating Token Index: 321