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

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

Neuron 3281 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: 1.7439. Min Range: -1.7439

Max Act: 1.7439. Min Act: -0.0000

Data Index: 342239 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.6577. Min Act: -0.0000

Data Index: 1124212 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.5581. Min Act: -0.0000

Data Index: 327954 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1324976 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1069812 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.4260. Min Act: -0.0000

Data Index: 979227 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.4773. Min Act: -0.0000

Data Index: 897728 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.4302. Min Act: -0.0000

Data Index: 572717 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.3377. Min Act: -0.0000

Data Index: 371612 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1171526 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.2510. Min Act: -0.0000

Data Index: 622628 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.3991. Min Act: -0.0000

Data Index: 222036 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.4093. Min Act: -0.0000

Data Index: 953012 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.3816. Min Act: -0.0000

Data Index: 778768 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.2811. Min Act: -0.0000

Data Index: 1277143 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.4497. Min Act: -0.0000

Data Index: 1016491 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1087162 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1086307 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.1791. Min Act: -0.0000

Data Index: 1290066 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.7439. Min Range: -1.7439

Max Act: 1.2475. Min Act: -0.0000

Data Index: 744079 (C4 (Web Text))

Max Activating Token Index: 779