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

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

Neuron 5504 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: 2.7922. Min Range: -2.7922

Max Act: 2.6708. Min Act: -0.0000

Data Index: 1565968 (Python Code)

Max Activating Token Index: 795

Text #1

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.7922. Min Act: -0.0000

Data Index: 1558044 (Python Code)

Max Activating Token Index: 950

Text #2

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.7461. Min Act: -0.0000

Data Index: 1432052 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.7041. Min Act: -0.0000

Data Index: 1372819 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.5743. Min Act: -0.0000

Data Index: 1456427 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.7696. Min Act: -0.0000

Data Index: 1577698 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.6319. Min Act: -0.0000

Data Index: 1403559 (Python Code)

Max Activating Token Index: 586

Text #7

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3536. Min Act: -0.0000

Data Index: 1570864 (Python Code)

Max Activating Token Index: 978

Text #8

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3566. Min Act: -0.0000

Data Index: 1553614 (Python Code)

Max Activating Token Index: 947

Text #9

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3224. Min Act: -0.0000

Data Index: 1459394 (Python Code)

Max Activating Token Index: 410

Text #10

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.4420. Min Act: -0.0000

Data Index: 1646414 (Python Code)

Max Activating Token Index: 557

Text #11

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.4154. Min Act: -0.0000

Data Index: 1381867 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.4050. Min Act: -0.0000

Data Index: 1378004 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3845. Min Act: -0.0000

Data Index: 1614176 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.4903. Min Act: -0.0000

Data Index: 1497705 (Python Code)

Max Activating Token Index: 606

Text #15

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3587. Min Act: -0.0000

Data Index: 1552849 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.2384. Min Act: -0.0000

Data Index: 1578739 (Python Code)

Max Activating Token Index: 657

Text #17

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.2291. Min Act: -0.0000

Data Index: 1567960 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3411. Min Act: -0.0000

Data Index: 1365409 (Python Code)

Max Activating Token Index: 466

Text #19

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.4420. Min Act: -0.0000

Data Index: 1412924 (Python Code)

Max Activating Token Index: 790