Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1153 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4903. Min Act: -0.0001

Data Index: 869157 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4946. Min Act: -0.0001

Data Index: 341574 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4692. Min Act: -0.0001

Data Index: 629980 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4118. Min Act: -0.0001

Data Index: 1001100 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4096. Min Act: -0.0001

Data Index: 92291 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4242. Min Act: -0.0001

Data Index: 1104948 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3986. Min Act: -0.0001

Data Index: 316212 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1233920 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3950. Min Act: -0.0001

Data Index: 791485 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3899. Min Act: -0.0001

Data Index: 303851 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4052. Min Act: -0.0001

Data Index: 545283 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3688. Min Act: -0.0001

Data Index: 940332 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4031. Min Act: -0.0001

Data Index: 475847 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3873. Min Act: -0.0001

Data Index: 244407 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3634. Min Act: -0.0001

Data Index: 87976 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.4183. Min Act: -0.0001

Data Index: 582844 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3567. Min Act: -0.0001

Data Index: 1130502 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3864. Min Act: -0.0001

Data Index: 1201667 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1100410 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.4946. Min Range: -0.4946

Max Act: 0.3628. Min Act: -0.0001

Data Index: 386257 (C4 (Web Text))

Max Activating Token Index: 462