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

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

Neuron 1172 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1378297 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1578773 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0103. Min Act: -0.0003

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1483328 (Python Code)

Max Activating Token Index: 816

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0079. Min Act: -0.0003

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1643779 (Python Code)

Max Activating Token Index: 681

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1244244 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1439139 (Python Code)

Max Activating Token Index: 651

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0067. Min Act: -0.0003

Data Index: 505089 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1641948 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1142759 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0066. Min Act: -0.0003

Data Index: 240053 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0064. Min Act: -0.0003

Data Index: 526434 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0065. Min Act: -0.0003

Data Index: 789480 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0064. Min Act: -0.0003

Data Index: 16596 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0062. Min Act: -0.0003

Data Index: 206405 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0062. Min Act: -0.0003

Data Index: 450105 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0061. Min Act: -0.0004

Data Index: 706918 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0062. Min Act: -0.0003

Data Index: 439557 (C4 (Web Text))

Max Activating Token Index: 824