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

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

Neuron 4669 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: 3.1286. Min Range: -3.1286

Max Act: 3.0929. Min Act: -0.0000

Data Index: 445031 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 3.1286. Min Range: -3.1286

Max Act: 3.1286. Min Act: -0.0000

Data Index: 635928 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.8244. Min Act: -0.0000

Data Index: 864821 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.7598. Min Act: -0.0000

Data Index: 1585109 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.6505. Min Act: -0.0000

Data Index: 66106 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.3993. Min Act: -0.0000

Data Index: 1448704 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.6365. Min Act: -0.0000

Data Index: 1652743 (Python Code)

Max Activating Token Index: 900

Text #7

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.6050. Min Act: -0.0000

Data Index: 1075793 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.5888. Min Act: -0.0000

Data Index: 618791 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.5537. Min Act: -0.0000

Data Index: 1374492 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.5383. Min Act: -0.0000

Data Index: 1628034 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.4201. Min Act: -0.0000

Data Index: 873990 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.5259. Min Act: -0.0000

Data Index: 1363440 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.6497. Min Act: -0.0000

Data Index: 1529336 (Python Code)

Max Activating Token Index: 612

Text #14

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.4783. Min Act: -0.0000

Data Index: 988792 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.4606. Min Act: -0.0000

Data Index: 1382088 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.4208. Min Act: -0.0000

Data Index: 738013 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.4340. Min Act: -0.0000

Data Index: 1081492 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.3833. Min Act: -0.0000

Data Index: 1616084 (Python Code)

Max Activating Token Index: 211

Text #19

Max Range: 3.1286. Min Range: -3.1286

Max Act: 2.5083. Min Act: -0.0000

Data Index: 1490262 (Python Code)

Max Activating Token Index: 268