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

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

Neuron 5265 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6359. Min Range: -3.6359

Max Act: 3.6359. Min Act: -0.0000

Data Index: 765587 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.7733. Min Act: -0.0000

Data Index: 819813 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.5086. Min Act: -0.0000

Data Index: 54049 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.1939. Min Act: -0.0000

Data Index: 1259608 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.3437. Min Act: -0.0000

Data Index: 1241076 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.2257. Min Act: -0.0000

Data Index: 887415 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.9487. Min Act: -0.0000

Data Index: 238784 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.0257. Min Act: -0.0000

Data Index: 683539 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.9105. Min Act: -0.0000

Data Index: 1575550 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 3.6359. Min Range: -3.6359

Max Act: 2.0312. Min Act: -0.0000

Data Index: 444924 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.6963. Min Act: -0.0000

Data Index: 1446228 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.7485. Min Act: -0.0000

Data Index: 1096338 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.5253. Min Act: -0.0000

Data Index: 1149529 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.7255. Min Act: -0.0000

Data Index: 1427122 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.7519. Min Act: -0.0000

Data Index: 1151495 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.6736. Min Act: -0.0000

Data Index: 155861 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.6855. Min Act: -0.0000

Data Index: 1549640 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.5743. Min Act: -0.0000

Data Index: 644525 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1196403 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 3.6359. Min Range: -3.6359

Max Act: 1.5704. Min Act: -0.0000

Data Index: 145727 (C4 (Web Text))

Max Activating Token Index: 948