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

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

Neuron 415 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0515. Min Act: -0.0001

Data Index: 290089 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0486. Min Act: -0.0001

Data Index: 703683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0441. Min Act: -0.0001

Data Index: 106103 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0431. Min Act: -0.0001

Data Index: 399284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0423. Min Act: -0.0001

Data Index: 285800 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0425. Min Act: -0.0001

Data Index: 755213 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0416. Min Act: -0.0001

Data Index: 87996 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0424. Min Act: -0.0001

Data Index: 485289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0415. Min Act: -0.0001

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1146004 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0405. Min Act: -0.0001

Data Index: 500017 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0404. Min Act: -0.0001

Data Index: 283195 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0403. Min Act: -0.0002

Data Index: 497763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0399. Min Act: -0.0001

Data Index: 901512 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0402. Min Act: -0.0001

Data Index: 37990 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0400. Min Act: -0.0001

Data Index: 15131 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1058025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0386. Min Act: -0.0001

Data Index: 420066 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0381. Min Act: -0.0001

Data Index: 428740 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0385. Min Act: -0.0001

Data Index: 847953 (C4 (Web Text))

Max Activating Token Index: 1023