Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5081 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.5463. Min Act: -0.0000

Data Index: 1035275 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.2271. Min Act: -0.0000

Data Index: 637010 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.0771. Min Act: -0.0000

Data Index: 1162392 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.1464. Min Act: -0.0000

Data Index: 876095 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.9672. Min Act: -0.0000

Data Index: 605329 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.0158. Min Act: -0.0000

Data Index: 650801 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.8647. Min Act: -0.0000

Data Index: 453898 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.7828. Min Act: -0.0000

Data Index: 777185 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.0221. Min Act: -0.0000

Data Index: 529279 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.7985. Min Act: -0.0000

Data Index: 633126 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.6475. Min Act: -0.0000

Data Index: 281262 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.7476. Min Act: -0.0000

Data Index: 1406240 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.7515. Min Act: -0.0000

Data Index: 416911 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.7129. Min Act: -0.0000

Data Index: 189858 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.8120. Min Act: -0.0000

Data Index: 40639 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.6635. Min Act: -0.0000

Data Index: 591351 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.5622. Min Act: -0.0000

Data Index: 468889 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.6287. Min Act: -0.0000

Data Index: 176353 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.5309. Min Act: -0.0000

Data Index: 1232810 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 2.5463. Min Range: -2.5463

Max Act: 1.5393. Min Act: -0.0000

Data Index: 530831 (C4 (Web Text))

Max Activating Token Index: 88