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

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

Neuron 4246 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: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1203323 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0453. Min Act: -0.0001

Data Index: 282341 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0443. Min Act: -0.0001

Data Index: 462861 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0438. Min Act: -0.0001

Data Index: 1146449 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0430. Min Act: -0.0001

Data Index: 347634 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0410. Min Act: -0.0001

Data Index: 67846 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0394. Min Act: -0.0001

Data Index: 44387 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0399. Min Act: -0.0001

Data Index: 105835 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0362. Min Act: -0.0001

Data Index: 866728 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0362. Min Act: -0.0001

Data Index: 143435 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1310378 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1351242 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0348. Min Act: -0.0001

Data Index: 362125 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1269756 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0327. Min Act: -0.0001

Data Index: 69670 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0329. Min Act: -0.0001

Data Index: 445884 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0324. Min Act: -0.0001

Data Index: 23791 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0326. Min Act: -0.0001

Data Index: 491954 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1276714 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0327. Min Act: -0.0001

Data Index: 959525 (C4 (Web Text))

Max Activating Token Index: 467