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

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

Neuron 443 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.0064. Min Act: -0.0001

Data Index: 1449771 (Python Code)

Max Activating Token Index: 579

Text #1

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.0471. Min Act: -0.0001

Data Index: 1590654 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1390584 (Python Code)

Max Activating Token Index: 488

Text #3

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.0985. Min Act: -0.0001

Data Index: 1411565 (Python Code)

Max Activating Token Index: 467

Text #4

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.0961. Min Act: -0.0001

Data Index: 1456445 (Python Code)

Max Activating Token Index: 300

Text #5

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1521594 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.0373. Min Act: -0.0001

Data Index: 1437240 (Python Code)

Max Activating Token Index: 438

Text #7

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1462132 (Python Code)

Max Activating Token Index: 860

Text #8

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.9250. Min Act: -0.0001

Data Index: 1400159 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.9927. Min Act: -0.0001

Data Index: 1458515 (Python Code)

Max Activating Token Index: 257

Text #10

Max Range: 1.1105. Min Range: -1.1105

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1369069 (Python Code)

Max Activating Token Index: 709

Text #11

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.9875. Min Act: -0.0001

Data Index: 1467719 (Python Code)

Max Activating Token Index: 532

Text #12

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.8927. Min Act: -0.0001

Data Index: 1433385 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.9521. Min Act: -0.0001

Data Index: 1503596 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1532243 (Python Code)

Max Activating Token Index: 814

Text #15

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1449719 (Python Code)

Max Activating Token Index: 428

Text #16

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.8427. Min Act: -0.0001

Data Index: 1426579 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.8707. Min Act: -0.0001

Data Index: 1636364 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1364224 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.9398. Min Act: -0.0001

Data Index: 1360320 (Python Code)

Max Activating Token Index: 394