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

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

Neuron 3790 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.7918. Min Act: -0.0003

Data Index: 1235231 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.7157. Min Act: -0.0003

Data Index: 99473 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6990. Min Act: -0.0003

Data Index: 848212 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6182. Min Act: -0.0003

Data Index: 675855 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6670. Min Act: -0.0003

Data Index: 17776 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5847. Min Act: -0.0003

Data Index: 938745 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6250. Min Act: -0.0004

Data Index: 94995 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6508. Min Act: -0.0003

Data Index: 404397 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5848. Min Act: -0.0003

Data Index: 1017818 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6037. Min Act: -0.0003

Data Index: 336627 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6157. Min Act: -0.0003

Data Index: 80709 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5772. Min Act: -0.0003

Data Index: 1245504 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6159. Min Act: -0.0003

Data Index: 866355 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6114. Min Act: -0.0003

Data Index: 274022 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6507. Min Act: -0.0003

Data Index: 186981 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5891. Min Act: -0.0003

Data Index: 833352 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6090. Min Act: -0.0003

Data Index: 843655 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5890. Min Act: -0.0003

Data Index: 633376 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.6064. Min Act: -0.0003

Data Index: 566539 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.7918. Min Range: -0.7918

Max Act: 0.5856. Min Act: -0.0003

Data Index: 351738 (C4 (Web Text))

Max Activating Token Index: 955