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

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

Neuron 4482 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: 0.7600. Min Range: -0.7600

Max Act: 0.7442. Min Act: -0.0002

Data Index: 11060 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.7600. Min Act: -0.0002

Data Index: 1236518 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.7185. Min Act: -0.0003

Data Index: 1150181 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.7117. Min Act: -0.0002

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6802. Min Act: -0.0002

Data Index: 693417 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6658. Min Act: -0.0002

Data Index: 67454 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6690. Min Act: -0.0002

Data Index: 575945 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6419. Min Act: -0.0002

Data Index: 1099829 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6493. Min Act: -0.0003

Data Index: 951598 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6423. Min Act: -0.0002

Data Index: 1127444 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6500. Min Act: -0.0002

Data Index: 1245762 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6498. Min Act: -0.0003

Data Index: 633056 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6315. Min Act: -0.0002

Data Index: 810778 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6214. Min Act: -0.0003

Data Index: 51332 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6107. Min Act: -0.0002

Data Index: 1029379 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5983. Min Act: -0.0002

Data Index: 1106215 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6186. Min Act: -0.0002

Data Index: 305744 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6066. Min Act: -0.0002

Data Index: 733583 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6105. Min Act: -0.0002

Data Index: 1187468 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5908. Min Act: -0.0003

Data Index: 798949 (C4 (Web Text))

Max Activating Token Index: 800