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

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

Neuron 1586 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.3883. Min Act: -0.0001

Data Index: 646216 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.5020. Min Act: -0.0001

Data Index: 68815 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.4436. Min Act: -0.0001

Data Index: 1264033 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2978. Min Act: -0.0001

Data Index: 1242276 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.4004. Min Act: -0.0001

Data Index: 989954 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.3066. Min Act: -0.0001

Data Index: 921508 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2077. Min Act: -0.0001

Data Index: 423835 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2676. Min Act: -0.0001

Data Index: 281666 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.3792. Min Act: -0.0001

Data Index: 219546 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2883. Min Act: -0.0001

Data Index: 1304048 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2374. Min Act: -0.0001

Data Index: 1154226 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1945. Min Act: -0.0001

Data Index: 1192753 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2460. Min Act: -0.0001

Data Index: 1563444 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2458. Min Act: -0.0001

Data Index: 909466 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2471. Min Act: -0.0001

Data Index: 53028 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1945. Min Act: -0.0001

Data Index: 420595 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2854. Min Act: -0.0001

Data Index: 1656002 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2566. Min Act: -0.0001

Data Index: 1254904 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.2476. Min Act: -0.0001

Data Index: 1296733 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 1.5020. Min Range: -1.5020

Max Act: 1.1358. Min Act: -0.0001

Data Index: 1087458 (C4 (Web Text))

Max Activating Token Index: 66