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

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

Neuron 142 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.8603. Min Act: -0.0001

Data Index: 72168 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7916. Min Act: -0.0001

Data Index: 1416414 (Python Code)

Max Activating Token Index: 457

Text #2

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7282. Min Act: -0.0001

Data Index: 1340760 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6884. Min Act: -0.0001

Data Index: 82894 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7014. Min Act: -0.0001

Data Index: 969492 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.7222. Min Act: -0.0001

Data Index: 945677 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6861. Min Act: -0.0001

Data Index: 562599 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6561. Min Act: -0.0001

Data Index: 443435 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6460. Min Act: -0.0001

Data Index: 162599 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6073. Min Act: -0.0001

Data Index: 444224 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1246887 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6545. Min Act: -0.0001

Data Index: 297447 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6538. Min Act: -0.0001

Data Index: 440803 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6365. Min Act: -0.0001

Data Index: 9157 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5968. Min Act: -0.0001

Data Index: 670417 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5768. Min Act: -0.0001

Data Index: 543638 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.4676. Min Act: -0.0001

Data Index: 810380 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5819. Min Act: -0.0001

Data Index: 363237 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.5964. Min Act: -0.0001

Data Index: 320011 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.8603. Min Range: -0.8603

Max Act: 0.6058. Min Act: -0.0001

Data Index: 1119146 (C4 (Web Text))

Max Activating Token Index: 117