Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 685 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3485. Min Act: -0.0001

Data Index: 1439342 (Python Code)

Max Activating Token Index: 581

Text #1

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.4312. Min Act: -0.0001

Data Index: 1523730 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3841. Min Act: -0.0001

Data Index: 1481540 (Python Code)

Max Activating Token Index: 679

Text #3

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.4388. Min Act: -0.0001

Data Index: 1493402 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3607. Min Act: -0.0001

Data Index: 1403825 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2600. Min Act: -0.0001

Data Index: 1559287 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2273. Min Act: -0.0001

Data Index: 1384040 (Python Code)

Max Activating Token Index: 692

Text #7

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.3086. Min Act: -0.0001

Data Index: 1465290 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2639. Min Act: -0.0001

Data Index: 1371584 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2193. Min Act: -0.0001

Data Index: 1464295 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1818. Min Act: -0.0001

Data Index: 1413442 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.0797. Min Act: -0.0001

Data Index: 1615733 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.2163. Min Act: -0.0001

Data Index: 1626586 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1472. Min Act: -0.0002

Data Index: 1649708 (Python Code)

Max Activating Token Index: 669

Text #14

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1244. Min Act: -0.0001

Data Index: 1442376 (Python Code)

Max Activating Token Index: 720

Text #15

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1513. Min Act: -0.0001

Data Index: 1362090 (Python Code)

Max Activating Token Index: 82

Text #16

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1468. Min Act: -0.0001

Data Index: 1427537 (Python Code)

Max Activating Token Index: 191

Text #17

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1117. Min Act: -0.0001

Data Index: 1366657 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1397. Min Act: -0.0001

Data Index: 1639020 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 1.4388. Min Range: -1.4388

Max Act: 1.1745. Min Act: -0.0001

Data Index: 1641407 (Python Code)

Max Activating Token Index: 365