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

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

Neuron 2795 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1580897 (Python Code)

Max Activating Token Index: 704

Text #1

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.7239. Min Act: -0.0001

Data Index: 1642692 (Python Code)

Max Activating Token Index: 45

Text #2

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1360637 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1428666 (Python Code)

Max Activating Token Index: 738

Text #4

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1630604 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6730. Min Act: -0.0001

Data Index: 1571238 (Python Code)

Max Activating Token Index: 556

Text #6

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1383418 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1477263 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6261. Min Act: -0.0001

Data Index: 785246 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1603372 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1606037 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6052. Min Act: -0.0001

Data Index: 1495654 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6203. Min Act: -0.0001

Data Index: 1616720 (Python Code)

Max Activating Token Index: 657

Text #13

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6395. Min Act: -0.0001

Data Index: 1542780 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6028. Min Act: -0.0001

Data Index: 1405672 (Python Code)

Max Activating Token Index: 472

Text #15

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6406. Min Act: -0.0001

Data Index: 1480672 (Python Code)

Max Activating Token Index: 400

Text #16

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6170. Min Act: -0.0001

Data Index: 1497709 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.5989. Min Act: -0.0000

Data Index: 436318 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6352. Min Act: -0.0001

Data Index: 1502694 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6322. Min Act: -0.0001

Data Index: 1429640 (Python Code)

Max Activating Token Index: 598