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

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

Neuron 2698 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.9138. Min Act: -0.0001

Data Index: 508601 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7943. Min Act: -0.0001

Data Index: 305076 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.7842. Min Act: -0.0001

Data Index: 521568 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5811. Min Act: -0.0001

Data Index: 1303743 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5045. Min Act: -0.0001

Data Index: 584609 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5880. Min Act: -0.0001

Data Index: 816694 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5805. Min Act: -0.0001

Data Index: 1274894 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6617. Min Act: -0.0001

Data Index: 712119 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5255. Min Act: -0.0001

Data Index: 401099 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4411. Min Act: -0.0001

Data Index: 872308 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.6778. Min Act: -0.0001

Data Index: 420265 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4298. Min Act: -0.0001

Data Index: 187904 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5088. Min Act: -0.0001

Data Index: 954361 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5006. Min Act: -0.0001

Data Index: 429381 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.5439. Min Act: -0.0001

Data Index: 110695 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3845. Min Act: -0.0001

Data Index: 624283 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.3612. Min Act: -0.0001

Data Index: 570117 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4285. Min Act: -0.0001

Data Index: 347011 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4900. Min Act: -0.0001

Data Index: 365045 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.9138. Min Range: -1.9138

Max Act: 1.4064. Min Act: -0.0001

Data Index: 904168 (C4 (Web Text))

Max Activating Token Index: 4