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

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

Neuron 3897 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.9145. Min Act: -0.0000

Data Index: 927888 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1011448 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.6064. Min Act: -0.0000

Data Index: 324153 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5567. Min Act: -0.0000

Data Index: 953168 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5394. Min Act: -0.0000

Data Index: 461215 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1144922 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5289. Min Act: -0.0000

Data Index: 279111 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4947. Min Act: -0.0000

Data Index: 826865 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5456. Min Act: -0.0000

Data Index: 991727 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5214. Min Act: -0.0000

Data Index: 876907 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4989. Min Act: -0.0000

Data Index: 583600 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4723. Min Act: -0.0000

Data Index: 459985 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4565. Min Act: -0.0000

Data Index: 534398 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1012603 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4790. Min Act: -0.0000

Data Index: 939804 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1089159 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5028. Min Act: -0.0000

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.5154. Min Act: -0.0000

Data Index: 613936 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1285212 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.9399. Min Range: -0.9399

Max Act: 0.4555. Min Act: -0.0000

Data Index: 619455 (C4 (Web Text))

Max Activating Token Index: 136