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

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

Neuron 2510 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1774. Min Act: -0.0001

Data Index: 926748 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1698. Min Act: -0.0001

Data Index: 421763 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1579. Min Act: -0.0001

Data Index: 20609 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1549. Min Act: -0.0001

Data Index: 990274 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1613. Min Act: -0.0001

Data Index: 624980 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1522. Min Act: -0.0001

Data Index: 1199870 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1539. Min Act: -0.0001

Data Index: 913764 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1415. Min Act: -0.0001

Data Index: 930181 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1107713 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1444. Min Act: -0.0001

Data Index: 440457 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1493. Min Act: -0.0001

Data Index: 105110 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1549. Min Act: -0.0001

Data Index: 453892 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1166999 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1382. Min Act: -0.0001

Data Index: 398106 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1635415 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1472. Min Act: -0.0001

Data Index: 9831 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1299. Min Act: -0.0001

Data Index: 393651 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1232032 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1493. Min Act: -0.0001

Data Index: 106220 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1515. Min Act: -0.0001

Data Index: 865301 (C4 (Web Text))

Max Activating Token Index: 503