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

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

Neuron 1798 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.5846. Min Act: -0.0001

Data Index: 460157 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1274910 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.4232. Min Act: -0.0001

Data Index: 623082 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3804. Min Act: -0.0001

Data Index: 1223526 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3396. Min Act: -0.0001

Data Index: 692726 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3505. Min Act: -0.0001

Data Index: 763919 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1677 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3669. Min Act: -0.0001

Data Index: 270018 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1198850 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3658. Min Act: -0.0001

Data Index: 1049716 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3396. Min Act: -0.0001

Data Index: 835993 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3456. Min Act: -0.0001

Data Index: 1291260 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3122. Min Act: -0.0001

Data Index: 38947 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3263. Min Act: -0.0001

Data Index: 644826 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3124. Min Act: -0.0001

Data Index: 314522 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3333. Min Act: -0.0001

Data Index: 986775 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1300157 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1152214 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3024. Min Act: -0.0001

Data Index: 1130307 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.5846. Min Range: -0.5846

Max Act: 0.3336. Min Act: -0.0001

Data Index: 11299 (C4 (Web Text))

Max Activating Token Index: 960