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

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

Neuron 2913 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: 2.5925. Min Range: -2.5925

Max Act: 2.5925. Min Act: -0.0000

Data Index: 1446202 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 2.5925. Min Range: -2.5925

Max Act: 2.2918. Min Act: -0.0000

Data Index: 1596008 (Python Code)

Max Activating Token Index: 834

Text #2

Max Range: 2.5925. Min Range: -2.5925

Max Act: 2.1304. Min Act: -0.0000

Data Index: 1431688 (Python Code)

Max Activating Token Index: 712

Text #3

Max Range: 2.5925. Min Range: -2.5925

Max Act: 2.0800. Min Act: -0.0000

Data Index: 1510410 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.9008. Min Act: -0.0000

Data Index: 1468273 (Python Code)

Max Activating Token Index: 941

Text #5

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.7235. Min Act: -0.0000

Data Index: 1429151 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.8922. Min Act: -0.0000

Data Index: 1564316 (Python Code)

Max Activating Token Index: 245

Text #7

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.7472. Min Act: -0.0000

Data Index: 944342 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.7306. Min Act: -0.0000

Data Index: 1650638 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1345205 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.5148. Min Act: -0.0000

Data Index: 1419636 (Python Code)

Max Activating Token Index: 608

Text #11

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.7750. Min Act: -0.0000

Data Index: 1495394 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.5736. Min Act: -0.0000

Data Index: 1484628 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.8687. Min Act: -0.0000

Data Index: 1599058 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.5608. Min Act: -0.0000

Data Index: 1489986 (Python Code)

Max Activating Token Index: 831

Text #15

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.7269. Min Act: -0.0000

Data Index: 1504550 (Python Code)

Max Activating Token Index: 584

Text #16

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1617531 (Python Code)

Max Activating Token Index: 773

Text #17

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1574994 (Python Code)

Max Activating Token Index: 488

Text #18

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.5161. Min Act: -0.0000

Data Index: 331380 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 2.5925. Min Range: -2.5925

Max Act: 1.6434. Min Act: -0.0000

Data Index: 1532775 (Python Code)

Max Activating Token Index: 749