Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3689 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.3535. Min Act: -0.0001

Data Index: 1095448 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2739. Min Act: -0.0001

Data Index: 60445 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1267478 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2934. Min Act: -0.0001

Data Index: 633860 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2750. Min Act: -0.0000

Data Index: 746074 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2439. Min Act: -0.0000

Data Index: 246266 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2477. Min Act: -0.0000

Data Index: 113158 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2397. Min Act: -0.0001

Data Index: 691919 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2247. Min Act: -0.0000

Data Index: 19746 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2362. Min Act: -0.0000

Data Index: 323911 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1113833 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2263. Min Act: -0.0001

Data Index: 791943 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2280. Min Act: -0.0001

Data Index: 1229400 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2215. Min Act: -0.0000

Data Index: 515262 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2227. Min Act: -0.0000

Data Index: 740062 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2074. Min Act: -0.0000

Data Index: 786062 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1105474 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.1953. Min Act: -0.0001

Data Index: 584246 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.2037. Min Act: -0.0000

Data Index: 711682 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.3535. Min Range: -0.3535

Max Act: 0.1944. Min Act: -0.0000

Data Index: 308557 (C4 (Web Text))

Max Activating Token Index: 470