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

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

Neuron 3335 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: 1.5865. Min Range: -1.5865

Max Act: 1.5865. Min Act: -0.0002

Data Index: 150432 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.5295. Min Act: -0.0002

Data Index: 378949 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.5459. Min Act: -0.0002

Data Index: 1326627 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.4622. Min Act: -0.0002

Data Index: 1072622 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.4663. Min Act: -0.0002

Data Index: 734388 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.3941. Min Act: -0.0002

Data Index: 1111822 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.4373. Min Act: -0.0002

Data Index: 824087 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.4078. Min Act: -0.0002

Data Index: 1343289 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.3662. Min Act: -0.0002

Data Index: 188156 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.3558. Min Act: -0.0002

Data Index: 937164 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.3092. Min Act: -0.0002

Data Index: 1232222 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.3133. Min Act: -0.0002

Data Index: 905739 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2562. Min Act: -0.0002

Data Index: 286400 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2817. Min Act: -0.0003

Data Index: 232798 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.3168. Min Act: -0.0002

Data Index: 1032687 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2894. Min Act: -0.0002

Data Index: 223305 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2733. Min Act: -0.0003

Data Index: 388073 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2848. Min Act: -0.0002

Data Index: 386949 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2636. Min Act: -0.0002

Data Index: 1175821 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 1.5865. Min Range: -1.5865

Max Act: 1.2432. Min Act: -0.0002

Data Index: 139549 (C4 (Web Text))

Max Activating Token Index: 3