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

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

Neuron 6109 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: 2.8153. Min Range: -2.8153

Max Act: 2.8153. Min Act: -0.0002

Data Index: 307274 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.6662. Min Act: -0.0002

Data Index: 680873 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.5530. Min Act: -0.0002

Data Index: 358472 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.4909. Min Act: -0.0002

Data Index: 326103 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.4415. Min Act: -0.0002

Data Index: 976992 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.3880. Min Act: -0.0002

Data Index: 1047926 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.3623. Min Act: -0.0002

Data Index: 477609 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.3615. Min Act: -0.0002

Data Index: 614016 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.3345. Min Act: -0.0003

Data Index: 1266781 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.3381. Min Act: -0.0002

Data Index: 810832 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2828. Min Act: -0.0002

Data Index: 1184546 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.3555. Min Act: -0.0002

Data Index: 579235 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2595. Min Act: -0.0002

Data Index: 970132 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.3098. Min Act: -0.0002

Data Index: 814043 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2608. Min Act: -0.0002

Data Index: 714704 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2818. Min Act: -0.0002

Data Index: 1250053 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2757. Min Act: -0.0002

Data Index: 1087595 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2800. Min Act: -0.0002

Data Index: 890351 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2123. Min Act: -0.0002

Data Index: 293223 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 2.8153. Min Range: -2.8153

Max Act: 2.2696. Min Act: -0.0002

Data Index: 787886 (C4 (Web Text))

Max Activating Token Index: 111