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

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

Neuron 3721 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.7970. Min Act: -0.0000

Data Index: 630857 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 3.7970. Min Range: -3.7970

Max Act: 3.0055. Min Act: -0.0000

Data Index: 110340 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.9883. Min Act: -0.0000

Data Index: 635193 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.9163. Min Act: -0.0000

Data Index: 346652 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.9581. Min Act: -0.0000

Data Index: 1319149 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.7771. Min Act: -0.0000

Data Index: 306433 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.7309. Min Act: -0.0000

Data Index: 166340 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.5684. Min Act: -0.0000

Data Index: 788402 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.4369. Min Act: -0.0000

Data Index: 883825 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.4550. Min Act: -0.0000

Data Index: 589449 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.4865. Min Act: -0.0000

Data Index: 15137 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.4465. Min Act: -0.0000

Data Index: 896059 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.3367. Min Act: -0.0000

Data Index: 157588 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.1828. Min Act: -0.0000

Data Index: 67043 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1302127 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.0293. Min Act: -0.0000

Data Index: 391751 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.2090. Min Act: -0.0000

Data Index: 40183 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 3.7970. Min Range: -3.7970

Max Act: 2.3127. Min Act: -0.0000

Data Index: 195745 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 3.7970. Min Range: -3.7970

Max Act: 1.9627. Min Act: -0.0000

Data Index: 1304324 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 3.7970. Min Range: -3.7970

Max Act: 1.9199. Min Act: -0.0000

Data Index: 650728 (C4 (Web Text))

Max Activating Token Index: 315