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

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

Neuron 2825 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9742. Min Act: -0.0001

Data Index: 524340 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9431. Min Act: -0.0001

Data Index: 159366 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.0249. Min Range: -1.0249

Max Act: 1.0249. Min Act: -0.0001

Data Index: 756254 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9314. Min Act: -0.0001

Data Index: 466958 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8006. Min Act: -0.0001

Data Index: 796736 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9056. Min Act: -0.0001

Data Index: 488978 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8273. Min Act: -0.0001

Data Index: 84057 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.9093. Min Act: -0.0001

Data Index: 531824 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8230. Min Act: -0.0001

Data Index: 14959 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8544. Min Act: -0.0001

Data Index: 619573 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7803. Min Act: -0.0001

Data Index: 1179669 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8065. Min Act: -0.0001

Data Index: 46224 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8275. Min Act: -0.0001

Data Index: 1274727 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8201. Min Act: -0.0001

Data Index: 1168141 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8214. Min Act: -0.0001

Data Index: 600314 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8237. Min Act: -0.0001

Data Index: 434836 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8653. Min Act: -0.0001

Data Index: 1160864 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7860. Min Act: -0.0001

Data Index: 1167413 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.8311. Min Act: -0.0001

Data Index: 604092 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.0249. Min Range: -1.0249

Max Act: 0.7773. Min Act: -0.0001

Data Index: 59097 (C4 (Web Text))

Max Activating Token Index: 844