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

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

Neuron 5785 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.5855. Min Act: -0.0000

Data Index: 864407 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.3131. Min Act: -0.0000

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.1558. Min Act: -0.0000

Data Index: 333475 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.2394. Min Act: -0.0000

Data Index: 821052 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.1440. Min Act: -0.0000

Data Index: 317786 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.0074. Min Act: -0.0000

Data Index: 943358 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.0691. Min Act: -0.0000

Data Index: 414513 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9078. Min Act: -0.0000

Data Index: 592533 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9747. Min Act: 0.0000

Data Index: 936951 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.0944. Min Act: -0.0000

Data Index: 1183954 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1345384 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9532. Min Act: -0.0000

Data Index: 982956 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.0587. Min Act: -0.0000

Data Index: 998911 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1638470 (Python Code)

Max Activating Token Index: 860

Text #14

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1576190 (Python Code)

Max Activating Token Index: 954

Text #15

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.0159. Min Act: 0.0000

Data Index: 495534 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9338. Min Act: -0.0000

Data Index: 872996 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.5855. Min Range: -1.5855

Max Act: 1.0042. Min Act: -0.0000

Data Index: 936238 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9924. Min Act: -0.0000

Data Index: 117418 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 1.5855. Min Range: -1.5855

Max Act: 0.9423. Min Act: -0.0000

Data Index: 25933 (C4 (Web Text))

Max Activating Token Index: 52