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

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

Neuron 3790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0493. Min Range: -1.0493

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1632590 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 1.0493. Min Range: -1.0493

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1517067 (Python Code)

Max Activating Token Index: 939

Text #2

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9681. Min Act: -0.0001

Data Index: 1617246 (Python Code)

Max Activating Token Index: 588

Text #3

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8978. Min Act: -0.0001

Data Index: 757301 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9287. Min Act: -0.0001

Data Index: 1519535 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1443161 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1386228 (Python Code)

Max Activating Token Index: 985

Text #7

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1561344 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1346598 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9054. Min Act: -0.0000

Data Index: 360548 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9321. Min Act: -0.0001

Data Index: 1410722 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1444174 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.9296. Min Act: -0.0001

Data Index: 228069 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1376250 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8445. Min Act: -0.0000

Data Index: 583875 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8680. Min Act: -0.0000

Data Index: 619638 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8413. Min Act: -0.0001

Data Index: 1475316 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8095. Min Act: -0.0001

Data Index: 563090 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8090. Min Act: -0.0001

Data Index: 682234 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.0493. Min Range: -1.0493

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1333238 (C4 (Web Text))

Max Activating Token Index: 127