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

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

Neuron 4518 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: 0.6610. Min Range: -0.6610

Max Act: 0.6610. Min Act: -0.0003

Data Index: 670240 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5808. Min Act: -0.0002

Data Index: 1174767 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5657. Min Act: -0.0003

Data Index: 1146805 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5592. Min Act: -0.0002

Data Index: 189998 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5475. Min Act: -0.0002

Data Index: 748871 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5612. Min Act: -0.0002

Data Index: 164652 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5382. Min Act: -0.0002

Data Index: 172214 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5499. Min Act: -0.0002

Data Index: 801591 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5454. Min Act: -0.0002

Data Index: 83018 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5318. Min Act: -0.0002

Data Index: 1194746 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5198. Min Act: -0.0002

Data Index: 1290272 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5350. Min Act: -0.0002

Data Index: 295572 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5289. Min Act: -0.0002

Data Index: 174193 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5171. Min Act: -0.0002

Data Index: 134017 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5187. Min Act: -0.0002

Data Index: 225000 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5297. Min Act: -0.0002

Data Index: 350396 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5172. Min Act: -0.0002

Data Index: 367421 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5174. Min Act: -0.0002

Data Index: 839043 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5078. Min Act: -0.0002

Data Index: 1236660 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5110. Min Act: -0.0002

Data Index: 263752 (C4 (Web Text))

Max Activating Token Index: 18