Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2333 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.3349. Min Act: -0.0000

Data Index: 740433 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.3127. Min Act: -0.0000

Data Index: 36245 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.2349. Min Act: -0.0000

Data Index: 495373 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.2800. Min Act: -0.0000

Data Index: 131362 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.1690. Min Act: -0.0000

Data Index: 1318008 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.2647. Min Act: -0.0000

Data Index: 1299011 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.1376. Min Act: -0.0000

Data Index: 1309676 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.3425. Min Act: -0.0000

Data Index: 391405 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.1994. Min Act: -0.0000

Data Index: 353708 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.0229. Min Act: -0.0000

Data Index: 245265 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.1270. Min Act: -0.0000

Data Index: 472769 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.1132. Min Act: -0.0000

Data Index: 435707 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.0748. Min Act: -0.0000

Data Index: 664763 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.0766. Min Act: -0.0000

Data Index: 641158 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.0584. Min Act: -0.0000

Data Index: 163044 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 2.3425. Min Range: -2.3425

Max Act: 1.9246. Min Act: -0.0000

Data Index: 722789 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.0089. Min Act: -0.0000

Data Index: 116826 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.0078. Min Act: -0.0000

Data Index: 272372 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 2.3425. Min Range: -2.3425

Max Act: 2.0728. Min Act: -0.0000

Data Index: 559145 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 2.3425. Min Range: -2.3425

Max Act: 1.9472. Min Act: -0.0000

Data Index: 421394 (C4 (Web Text))

Max Activating Token Index: 852