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

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

Neuron 644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.3431. Min Act: -0.0001

Data Index: 632051 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.0942. Min Act: -0.0001

Data Index: 319540 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.1550. Min Act: -0.0001

Data Index: 999837 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.1626. Min Act: -0.0001

Data Index: 649267 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.1040. Min Act: -0.0000

Data Index: 755131 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.1322. Min Act: -0.0001

Data Index: 1306795 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.1296. Min Act: -0.0001

Data Index: 968059 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.0385. Min Act: -0.0001

Data Index: 898029 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9830. Min Act: -0.0001

Data Index: 4396 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9854. Min Act: -0.0001

Data Index: 202425 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.0480. Min Act: -0.0001

Data Index: 684445 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9792. Min Act: -0.0000

Data Index: 725386 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 1.3431. Min Range: -1.3431

Max Act: 1.0054. Min Act: -0.0001

Data Index: 1048801 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9593. Min Act: -0.0000

Data Index: 1653390 (Python Code)

Max Activating Token Index: 952

Text #14

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1274349 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9943. Min Act: -0.0001

Data Index: 455028 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9789. Min Act: -0.0000

Data Index: 618427 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1279867 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.9309. Min Act: -0.0001

Data Index: 523592 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 1.3431. Min Range: -1.3431

Max Act: 0.8851. Min Act: -0.0001

Data Index: 78905 (C4 (Web Text))

Max Activating Token Index: 319