Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5928 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1251. Min Act: -0.0001

Data Index: 356741 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1056087 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1260. Min Act: -0.0000

Data Index: 630065 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1161. Min Act: -0.0000

Data Index: 614980 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1117. Min Act: -0.0001

Data Index: 677768 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1119. Min Act: -0.0000

Data Index: 885612 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1090. Min Act: -0.0000

Data Index: 303187 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1143. Min Act: -0.0001

Data Index: 414135 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0997. Min Act: -0.0000

Data Index: 562317 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1122. Min Act: -0.0000

Data Index: 261056 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0979. Min Act: -0.0000

Data Index: 578457 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0999. Min Act: -0.0000

Data Index: 844795 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0939. Min Act: -0.0000

Data Index: 532253 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0941. Min Act: -0.0000

Data Index: 183684 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0984. Min Act: -0.0001

Data Index: 640563 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0916. Min Act: -0.0000

Data Index: 570797 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1325254 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1161650 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1172019 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1349081 (C4 (Web Text))

Max Activating Token Index: 417