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

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

Neuron 4943 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: 0.4434. Min Range: -0.4434

Max Act: 0.4434. Min Act: -0.0000

Data Index: 504531 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3768. Min Act: -0.0000

Data Index: 893808 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3435. Min Act: -0.0000

Data Index: 938288 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3501. Min Act: -0.0000

Data Index: 60725 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1236183 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3330. Min Act: -0.0000

Data Index: 306520 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3369. Min Act: -0.0000

Data Index: 689426 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3221. Min Act: -0.0000

Data Index: 624788 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1195789 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3161. Min Act: -0.0000

Data Index: 835666 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1215365 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3111. Min Act: -0.0000

Data Index: 584255 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3192. Min Act: -0.0000

Data Index: 865068 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3059. Min Act: -0.0000

Data Index: 604690 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1016707 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.2912. Min Act: -0.0000

Data Index: 926454 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3003. Min Act: -0.0000

Data Index: 679096 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.3104. Min Act: -0.0000

Data Index: 533885 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.2986. Min Act: -0.0000

Data Index: 383756 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.4434. Min Range: -0.4434

Max Act: 0.2893. Min Act: -0.0000

Data Index: 62798 (C4 (Web Text))

Max Activating Token Index: 756