Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1684 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4785. Min Act: -0.0000

Data Index: 311632 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3668. Min Act: -0.0001

Data Index: 849479 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1118581 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3587. Min Act: -0.0000

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3535. Min Act: -0.0000

Data Index: 999801 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3323. Min Act: -0.0000

Data Index: 750245 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3481. Min Act: -0.0000

Data Index: 1048993 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1351325 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3427. Min Act: -0.0000

Data Index: 325421 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3507. Min Act: -0.0000

Data Index: 686366 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3326. Min Act: -0.0000

Data Index: 41012 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3357. Min Act: -0.0001

Data Index: 1024316 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3232. Min Act: -0.0000

Data Index: 491868 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3290. Min Act: -0.0000

Data Index: 32509 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1194660 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3182. Min Act: -0.0000

Data Index: 75797 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3155. Min Act: -0.0001

Data Index: 1007849 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1210114 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3199. Min Act: -0.0001

Data Index: 1655 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1200222 (C4 (Web Text))

Max Activating Token Index: 383