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

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

Neuron 1474 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1971. Min Range: -6.1971

Max Act: 6.1971. Min Act: -0.0001

Data Index: 691521 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.9893. Min Act: -0.0001

Data Index: 928289 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.9008. Min Act: -0.0000

Data Index: 464911 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.6008. Min Act: -0.0001

Data Index: 1301706 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.2671. Min Act: -0.0001

Data Index: 908110 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.5711. Min Act: -0.0001

Data Index: 1191951 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.4981. Min Act: -0.0000

Data Index: 1344281 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.2072. Min Act: -0.0000

Data Index: 1262712 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.5393. Min Act: -0.0001

Data Index: 27824 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 6.1971. Min Range: -6.1971

Max Act: 4.8571. Min Act: -0.0000

Data Index: 404546 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.6586. Min Act: -0.0000

Data Index: 1066439 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.0319. Min Act: -0.0001

Data Index: 116055 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 6.1971. Min Range: -6.1971

Max Act: 4.8132. Min Act: -0.0001

Data Index: 771386 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.3396. Min Act: -0.0001

Data Index: 197118 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 6.1971. Min Range: -6.1971

Max Act: 4.6051. Min Act: -0.0001

Data Index: 6303 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 6.1971. Min Range: -6.1971

Max Act: 4.9442. Min Act: -0.0001

Data Index: 435147 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 6.1971. Min Range: -6.1971

Max Act: 4.4180. Min Act: -0.0000

Data Index: 402686 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.2608. Min Act: -0.0001

Data Index: 921920 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 6.1971. Min Range: -6.1971

Max Act: 5.2442. Min Act: -0.0000

Data Index: 475143 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 6.1971. Min Range: -6.1971

Max Act: 4.4599. Min Act: -0.0001

Data Index: 1206924 (C4 (Web Text))

Max Activating Token Index: 998