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

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

Neuron 2607 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: 0.1934. Min Range: -0.1934

Max Act: 0.1826. Min Act: -0.0001

Data Index: 479507 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0001

Data Index: 27533 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1921. Min Act: -0.0001

Data Index: 736883 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1164399 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1770. Min Act: -0.0001

Data Index: 662444 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1760. Min Act: -0.0001

Data Index: 511492 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1693. Min Act: -0.0001

Data Index: 864877 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1182513 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1102720 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1658. Min Act: -0.0001

Data Index: 500560 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1489. Min Act: -0.0001

Data Index: 79673 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1562. Min Act: -0.0001

Data Index: 257745 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1412. Min Act: -0.0001

Data Index: 276780 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1443. Min Act: -0.0001

Data Index: 185941 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1294. Min Act: -0.0001

Data Index: 218698 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1494. Min Act: -0.0001

Data Index: 258061 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1430. Min Act: -0.0001

Data Index: 201341 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1492. Min Act: -0.0001

Data Index: 170216 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1432. Min Act: -0.0001

Data Index: 977679 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1431. Min Act: -0.0001

Data Index: 708885 (C4 (Web Text))

Max Activating Token Index: 344