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

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

Neuron 2292 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4489. Min Range: -1.4489

Max Act: 1.4489. Min Act: -0.0000

Data Index: 614518 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 1.4489. Min Range: -1.4489

Max Act: 1.2069. Min Act: -0.0000

Data Index: 244301 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 1.4489. Min Range: -1.4489

Max Act: 1.0743. Min Act: -0.0000

Data Index: 213373 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 1.4489. Min Range: -1.4489

Max Act: 1.0458. Min Act: -0.0000

Data Index: 164880 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.4489. Min Range: -1.4489

Max Act: 1.0538. Min Act: -0.0000

Data Index: 3930 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.4489. Min Range: -1.4489

Max Act: 1.0166. Min Act: -0.0000

Data Index: 887480 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.9115. Min Act: -0.0000

Data Index: 122502 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.9603. Min Act: -0.0000

Data Index: 704810 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.9231. Min Act: -0.0000

Data Index: 162602 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.9235. Min Act: -0.0000

Data Index: 519530 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1030891 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1271511 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.8791. Min Act: -0.0000

Data Index: 755409 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.8380. Min Act: -0.0000

Data Index: 659933 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.7860. Min Act: -0.0000

Data Index: 949076 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1018995 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.8270. Min Act: -0.0000

Data Index: 172807 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.7988. Min Act: -0.0000

Data Index: 249100 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1297589 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.4489. Min Range: -1.4489

Max Act: 0.7927. Min Act: -0.0000

Data Index: 497256 (C4 (Web Text))

Max Activating Token Index: 624