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

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

Neuron 2455 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.5954. Min Act: -0.0000

Data Index: 856316 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.8071. Min Act: -0.0000

Data Index: 742430 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.4836. Min Act: -0.0000

Data Index: 979153 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.0044. Min Act: -0.0000

Data Index: 188935 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.0532. Min Act: -0.0000

Data Index: 817462 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.8071. Min Range: -2.8071

Max Act: 2.0318. Min Act: -0.0000

Data Index: 466901 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.9396. Min Act: -0.0000

Data Index: 837953 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.9174. Min Act: -0.0000

Data Index: 482165 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.9064. Min Act: -0.0000

Data Index: 1322692 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.8378. Min Act: -0.0000

Data Index: 1338730 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.7174. Min Act: -0.0000

Data Index: 827500 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.8150. Min Act: -0.0000

Data Index: 1177481 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.7899. Min Act: -0.0000

Data Index: 177844 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.7816. Min Act: -0.0000

Data Index: 561512 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.8505. Min Act: -0.0000

Data Index: 737095 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.6158. Min Act: -0.0000

Data Index: 233155 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.6885. Min Act: -0.0000

Data Index: 490797 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.7190. Min Act: -0.0000

Data Index: 1071538 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.6198. Min Act: -0.0000

Data Index: 471720 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 2.8071. Min Range: -2.8071

Max Act: 1.6793. Min Act: -0.0000

Data Index: 664725 (C4 (Web Text))

Max Activating Token Index: 826