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

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

Neuron 4171 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: 1.5790. Min Range: -1.5790

Max Act: 1.5413. Min Act: -0.0002

Data Index: 553525 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.5790. Min Act: -0.0002

Data Index: 354084 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4770. Min Act: -0.0002

Data Index: 635200 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4778. Min Act: -0.0002

Data Index: 1078779 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4702. Min Act: -0.0002

Data Index: 401695 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4464. Min Act: -0.0002

Data Index: 819932 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4641. Min Act: -0.0002

Data Index: 1071481 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4542. Min Act: -0.0002

Data Index: 1012364 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4489. Min Act: -0.0002

Data Index: 1230449 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4256. Min Act: -0.0002

Data Index: 1048227 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4305. Min Act: -0.0002

Data Index: 882395 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4215. Min Act: -0.0002

Data Index: 230365 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4119. Min Act: -0.0002

Data Index: 362226 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4098. Min Act: -0.0002

Data Index: 786318 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.4145. Min Act: -0.0002

Data Index: 808621 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.3956. Min Act: -0.0002

Data Index: 105800 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.3818. Min Act: -0.0002

Data Index: 285324 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.3648. Min Act: -0.0002

Data Index: 386374 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.3752. Min Act: -0.0002

Data Index: 1211466 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.5790. Min Range: -1.5790

Max Act: 1.3805. Min Act: -0.0002

Data Index: 876974 (C4 (Web Text))

Max Activating Token Index: 318