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

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

Neuron 946 in Layer 1

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: 3.7244. Min Range: -3.7244

Max Act: 3.7244. Min Act: -0.0002

Data Index: 166600 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.4746. Min Act: -0.0002

Data Index: 88780 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.4746. Min Act: -0.0002

Data Index: 1488083 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.5539. Min Act: -0.0003

Data Index: 490186 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.5094. Min Act: -0.0003

Data Index: 157503 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.2893. Min Act: -0.0002

Data Index: 325218 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.3477. Min Act: -0.0002

Data Index: 1110656 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.2349. Min Act: -0.0002

Data Index: 343527 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1335. Min Act: -0.0002

Data Index: 303672 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1774. Min Act: -0.0002

Data Index: 1323904 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1245. Min Act: -0.0002

Data Index: 821743 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0784. Min Act: -0.0002

Data Index: 314998 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1018. Min Act: -0.0003

Data Index: 962258 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0521. Min Act: -0.0002

Data Index: 66648 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1286. Min Act: -0.0002

Data Index: 22735 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0375. Min Act: -0.0002

Data Index: 991512 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.1018. Min Act: -0.0002

Data Index: 281272 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 3.7244. Min Range: -3.7244

Max Act: 3.0450. Min Act: -0.0002

Data Index: 1027078 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 3.7244. Min Range: -3.7244

Max Act: 2.9815. Min Act: -0.0002

Data Index: 1079560 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 3.7244. Min Range: -3.7244

Max Act: 2.9371. Min Act: -0.0002

Data Index: 1188761 (C4 (Web Text))

Max Activating Token Index: 428