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

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

Neuron 3814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.4322. Min Act: -0.0000

Data Index: 760466 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.4051. Min Act: -0.0000

Data Index: 174825 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.3253. Min Act: -0.0000

Data Index: 731134 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.2615. Min Act: -0.0000

Data Index: 1320127 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1979. Min Act: -0.0000

Data Index: 406159 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9991. Min Act: -0.0000

Data Index: 1254836 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1813. Min Act: -0.0000

Data Index: 583435 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1807. Min Act: -0.0000

Data Index: 482977 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1724. Min Act: -0.0000

Data Index: 1256727 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.1484. Min Act: -0.0000

Data Index: 862852 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0046. Min Act: -0.0000

Data Index: 1046035 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9545. Min Act: -0.0000

Data Index: 1355662 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0501. Min Act: -0.0000

Data Index: 1173697 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0345. Min Act: -0.0000

Data Index: 206851 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9296. Min Act: -0.0000

Data Index: 1331275 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.8217. Min Act: -0.0000

Data Index: 1226595 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.9240. Min Act: -0.0000

Data Index: 1091846 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.7970. Min Act: -0.0000

Data Index: 361972 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 2.4322. Min Range: -2.4322

Max Act: 2.0043. Min Act: -0.0000

Data Index: 60340 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 2.4322. Min Range: -2.4322

Max Act: 1.7571. Min Act: -0.0000

Data Index: 666609 (C4 (Web Text))

Max Activating Token Index: 446