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

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

Neuron 1488 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: 1.4282. Min Range: -1.4282

Max Act: 1.4282. Min Act: -0.0001

Data Index: 1597072 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3216. Min Act: -0.0001

Data Index: 1438657 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3336. Min Act: -0.0001

Data Index: 1481915 (Python Code)

Max Activating Token Index: 558

Text #3

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2818. Min Act: -0.0001

Data Index: 1505627 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.3127. Min Act: -0.0001

Data Index: 1361845 (Python Code)

Max Activating Token Index: 980

Text #5

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1870. Min Act: -0.0001

Data Index: 123368 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2214. Min Act: -0.0001

Data Index: 7812 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1521. Min Act: -0.0001

Data Index: 1168445 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1930. Min Act: -0.0001

Data Index: 317933 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1386. Min Act: -0.0001

Data Index: 1493429 (Python Code)

Max Activating Token Index: 550

Text #10

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.2443. Min Act: -0.0001

Data Index: 686233 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1678. Min Act: -0.0001

Data Index: 745503 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1092. Min Act: -0.0001

Data Index: 1573894 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1414. Min Act: -0.0001

Data Index: 1199098 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1004. Min Act: -0.0001

Data Index: 833073 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1372. Min Act: -0.0001

Data Index: 839445 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0912. Min Act: -0.0001

Data Index: 593700 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1009. Min Act: -0.0001

Data Index: 935147 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.0929. Min Act: -0.0001

Data Index: 444765 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 1.4282. Min Range: -1.4282

Max Act: 1.1147. Min Act: -0.0001

Data Index: 6503 (C4 (Web Text))

Max Activating Token Index: 336