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

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

Neuron 1363 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4642. Min Range: -2.4642

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1296198 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.4642. Min Range: -2.4642

Max Act: 2.3338. Min Act: -0.0000

Data Index: 976538 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 2.4642. Min Range: -2.4642

Max Act: 2.2097. Min Act: -0.0000

Data Index: 646749 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.9339. Min Act: -0.0000

Data Index: 1006632 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1170617 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.8555. Min Act: -0.0000

Data Index: 1055842 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.8396. Min Act: -0.0000

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7832. Min Act: -0.0000

Data Index: 562022 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7735. Min Act: -0.0000

Data Index: 823107 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7893. Min Act: -0.0000

Data Index: 1167577 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7351. Min Act: -0.0000

Data Index: 1013157 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.8805. Min Act: -0.0000

Data Index: 106121 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7061. Min Act: -0.0000

Data Index: 316344 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.7955. Min Act: -0.0000

Data Index: 356027 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6921. Min Act: -0.0000

Data Index: 1233539 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6931. Min Act: -0.0000

Data Index: 206816 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6629. Min Act: -0.0000

Data Index: 806198 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6248. Min Act: -0.0000

Data Index: 104123 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6051. Min Act: -0.0000

Data Index: 747998 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 2.4642. Min Range: -2.4642

Max Act: 1.6453. Min Act: -0.0000

Data Index: 70267 (C4 (Web Text))

Max Activating Token Index: 795