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

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

Neuron 4288 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2669. Min Act: -0.0000

Data Index: 895183 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2526. Min Act: -0.0000

Data Index: 391628 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1336874 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2432. Min Act: -0.0000

Data Index: 1304303 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2473. Min Act: -0.0000

Data Index: 248428 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2393. Min Act: -0.0000

Data Index: 395104 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1511275 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2364. Min Act: -0.0000

Data Index: 551679 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1033152 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1553452 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1467942 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1497487 (Python Code)

Max Activating Token Index: 453

Text #12

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1394716 (Python Code)

Max Activating Token Index: 679

Text #13

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2240. Min Act: -0.0000

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1352633 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1404668 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2196. Min Act: -0.0000

Data Index: 131989 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2280. Min Act: -0.0000

Data Index: 234693 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1144584 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.2669. Min Range: -0.2669

Max Act: 0.2166. Min Act: -0.0000

Data Index: 727111 (C4 (Web Text))

Max Activating Token Index: 993