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

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

Neuron 3932 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: 1.6049. Min Range: -1.6049

Max Act: 1.6049. Min Act: -0.0000

Data Index: 1581361 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.5577. Min Act: -0.0000

Data Index: 1578071 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.4116. Min Act: -0.0000

Data Index: 854409 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1445088 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1536228 (Python Code)

Max Activating Token Index: 656

Text #5

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.4204. Min Act: -0.0000

Data Index: 52379 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1480202 (Python Code)

Max Activating Token Index: 745

Text #7

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1471414 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2310. Min Act: -0.0000

Data Index: 1085117 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2946. Min Act: -0.0000

Data Index: 37772 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2788. Min Act: -0.0000

Data Index: 1541704 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2728. Min Act: -0.0000

Data Index: 961559 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2691. Min Act: -0.0000

Data Index: 40028 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1613549 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.1809. Min Act: -0.0000

Data Index: 721998 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.4397. Min Act: -0.0000

Data Index: 1397975 (Python Code)

Max Activating Token Index: 439

Text #16

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1261279 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2386. Min Act: -0.0000

Data Index: 1015931 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1509801 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 1.6049. Min Range: -1.6049

Max Act: 1.2286. Min Act: -0.0000

Data Index: 491369 (C4 (Web Text))

Max Activating Token Index: 834