Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1048 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3617. Min Act: -0.0003

Data Index: 1570862 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3615. Min Act: -0.0003

Data Index: 1445674 (Python Code)

Max Activating Token Index: 656

Text #2

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3465. Min Act: -0.0003

Data Index: 1554497 (Python Code)

Max Activating Token Index: 495

Text #3

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3581. Min Act: -0.0003

Data Index: 1503714 (Python Code)

Max Activating Token Index: 441

Text #4

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3388. Min Act: -0.0003

Data Index: 1364824 (Python Code)

Max Activating Token Index: 935

Text #5

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3502. Min Act: -0.0003

Data Index: 1583597 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3692. Min Act: -0.0003

Data Index: 1634303 (Python Code)

Max Activating Token Index: 297

Text #7

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3193. Min Act: -0.0003

Data Index: 1499218 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3400. Min Act: -0.0003

Data Index: 1653937 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3395. Min Act: -0.0003

Data Index: 1610433 (Python Code)

Max Activating Token Index: 951

Text #10

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3254. Min Act: -0.0003

Data Index: 1541139 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3134. Min Act: -0.0003

Data Index: 1471543 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3326. Min Act: -0.0003

Data Index: 1565897 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3274. Min Act: -0.0003

Data Index: 1462842 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3288. Min Act: -0.0003

Data Index: 1460361 (Python Code)

Max Activating Token Index: 532

Text #15

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3372. Min Act: -0.0003

Data Index: 1476937 (Python Code)

Max Activating Token Index: 577

Text #16

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3234. Min Act: -0.0003

Data Index: 1454213 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3360. Min Act: -0.0003

Data Index: 1561336 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.3346. Min Act: -0.0003

Data Index: 1595521 (Python Code)

Max Activating Token Index: 353

Text #19

Max Range: 0.3692. Min Range: -0.3692

Max Act: 0.2967. Min Act: -0.0003

Data Index: 1647958 (Python Code)

Max Activating Token Index: 245