Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2743 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.3651. Min Act: -0.0000

Data Index: 412454 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1571. Min Act: -0.0000

Data Index: 97705 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1630. Min Act: -0.0000

Data Index: 198406 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1375. Min Act: -0.0000

Data Index: 141023 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1193830 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.3651. Min Range: -1.3651

Max Act: 1.0818. Min Act: -0.0000

Data Index: 293777 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.9398. Min Act: -0.0000

Data Index: 390919 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1179970 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.8652. Min Act: -0.0000

Data Index: 494024 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.8454. Min Act: -0.0000

Data Index: 450235 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.8108. Min Act: -0.0000

Data Index: 519227 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.8539. Min Act: -0.0000

Data Index: 752063 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1305300 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.7846. Min Act: -0.0000

Data Index: 439524 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.8265. Min Act: -0.0000

Data Index: 916340 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.7946. Min Act: -0.0000

Data Index: 964351 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.7729. Min Act: -0.0000

Data Index: 535648 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.7957. Min Act: -0.0000

Data Index: 437999 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1083395 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 1.3651. Min Range: -1.3651

Max Act: 0.7197. Min Act: -0.0000

Data Index: 121083 (C4 (Web Text))

Max Activating Token Index: 755