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

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

Neuron 4617 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: 1.6814. Min Range: -1.6814

Max Act: 1.6802. Min Act: -0.0002

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.6814. Min Act: -0.0002

Data Index: 917862 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.6194. Min Act: -0.0002

Data Index: 468021 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.6198. Min Act: -0.0002

Data Index: 1132794 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.5812. Min Act: -0.0002

Data Index: 1169631 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4796. Min Act: -0.0002

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4395. Min Act: -0.0002

Data Index: 462237 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4938. Min Act: -0.0002

Data Index: 234566 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4591. Min Act: -0.0002

Data Index: 1051046 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4337. Min Act: -0.0002

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4572. Min Act: -0.0002

Data Index: 102694 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.3950. Min Act: -0.0002

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.3799. Min Act: -0.0002

Data Index: 168364 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4378. Min Act: -0.0002

Data Index: 547264 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4097. Min Act: -0.0002

Data Index: 359345 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.4044. Min Act: -0.0002

Data Index: 279142 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.3832. Min Act: -0.0002

Data Index: 77997 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.3530. Min Act: -0.0002

Data Index: 360708 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.3593. Min Act: -0.0002

Data Index: 109502 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.6814. Min Range: -1.6814

Max Act: 1.3584. Min Act: -0.0002

Data Index: 1192439 (C4 (Web Text))

Max Activating Token Index: 797