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

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

Neuron 3238 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1517387 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1450063 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1419205 (Python Code)

Max Activating Token Index: 526

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1648759 (Python Code)

Max Activating Token Index: 502

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1429086 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0521. Min Act: -0.0002

Data Index: 922372 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1514808 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1493190 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0505. Min Act: -0.0002

Data Index: 525129 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1487403 (Python Code)

Max Activating Token Index: 283

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0491. Min Act: -0.0002

Data Index: 103516 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1488299 (Python Code)

Max Activating Token Index: 381

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1526580 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1368452 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0505. Min Act: -0.0002

Data Index: 181981 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1422691 (Python Code)

Max Activating Token Index: 159

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1470338 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1397707 (Python Code)

Max Activating Token Index: 299

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1373963 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1481172 (Python Code)

Max Activating Token Index: 492