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

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

Neuron 4169 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: 0.4852. Min Range: -0.4852

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1629680 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.4137. Min Act: -0.0000

Data Index: 159684 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1626906 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1612329 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1444120 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3191. Min Act: -0.0000

Data Index: 829843 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1437612 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3112. Min Act: -0.0000

Data Index: 409193 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1040378 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3039. Min Act: -0.0000

Data Index: 847816 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1566155 (Python Code)

Max Activating Token Index: 619

Text #11

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.3142. Min Act: -0.0000

Data Index: 1435613 (Python Code)

Max Activating Token Index: 376

Text #12

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1085263 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2825. Min Act: -0.0000

Data Index: 577366 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2705. Min Act: -0.0000

Data Index: 300164 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2608. Min Act: -0.0000

Data Index: 778217 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2646. Min Act: -0.0000

Data Index: 893247 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1452926 (Python Code)

Max Activating Token Index: 471

Text #18

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2660. Min Act: -0.0000

Data Index: 683151 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.4852. Min Range: -0.4852

Max Act: 0.2431. Min Act: -0.0000

Data Index: 309737 (C4 (Web Text))

Max Activating Token Index: 945