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

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

Neuron 3786 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: 1.2260. Min Range: -1.2260

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1272834 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.1792. Min Act: -0.0000

Data Index: 965461 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1110100 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.2260. Min Range: -1.2260

Max Act: 1.0569. Min Act: -0.0000

Data Index: 824287 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9431. Min Act: -0.0001

Data Index: 1123876 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.9269. Min Act: -0.0000

Data Index: 771599 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8955. Min Act: -0.0001

Data Index: 955992 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8533. Min Act: -0.0001

Data Index: 775223 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8835. Min Act: -0.0001

Data Index: 385665 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8148. Min Act: -0.0000

Data Index: 701476 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8504. Min Act: -0.0000

Data Index: 124379 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8350. Min Act: -0.0000

Data Index: 754119 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8557. Min Act: -0.0001

Data Index: 129348 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1130099 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.8151. Min Act: -0.0001

Data Index: 318133 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1347581 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.7630. Min Act: -0.0001

Data Index: 616419 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1018285 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.7311. Min Act: -0.0000

Data Index: 237561 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.2260. Min Range: -1.2260

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1248622 (C4 (Web Text))

Max Activating Token Index: 484