Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2017 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.4692. Min Act: -0.0001

Data Index: 1184866 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3279. Min Act: -0.0001

Data Index: 406276 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3282. Min Act: -0.0001

Data Index: 255351 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3032. Min Act: -0.0000

Data Index: 790706 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2937. Min Act: -0.0000

Data Index: 979471 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3377. Min Act: -0.0001

Data Index: 40189 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2964. Min Act: -0.0001

Data Index: 468175 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2862. Min Act: -0.0001

Data Index: 301167 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2694. Min Act: -0.0000

Data Index: 422806 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2916. Min Act: -0.0000

Data Index: 628110 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2829. Min Act: -0.0001

Data Index: 77030 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1237949 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2701. Min Act: -0.0001

Data Index: 896200 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.3060. Min Act: -0.0001

Data Index: 644922 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1331082 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2562. Min Act: -0.0001

Data Index: 431923 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2738. Min Act: -0.0001

Data Index: 478351 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1070323 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2730. Min Act: -0.0001

Data Index: 814125 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.4692. Min Range: -0.4692

Max Act: 0.2699. Min Act: -0.0001

Data Index: 1024670 (C4 (Web Text))

Max Activating Token Index: 509