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

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

Neuron 992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.2195. Min Act: -0.0001

Data Index: 760969 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0424. Min Act: -0.0001

Data Index: 159845 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0931. Min Act: -0.0001

Data Index: 171215 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0194. Min Act: -0.0001

Data Index: 911883 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0881. Min Act: -0.0001

Data Index: 887705 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0595. Min Act: -0.0001

Data Index: 1354458 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0273. Min Act: -0.0001

Data Index: 826079 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.2195. Min Range: -1.2195

Max Act: 1.0347. Min Act: -0.0001

Data Index: 1031472 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.9917. Min Act: -0.0001

Data Index: 1275953 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.9803. Min Act: -0.0001

Data Index: 272202 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.9856. Min Act: -0.0001

Data Index: 1128956 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.9469. Min Act: -0.0001

Data Index: 983367 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.9182. Min Act: -0.0001

Data Index: 686470 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8876. Min Act: -0.0001

Data Index: 1210781 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8874. Min Act: -0.0001

Data Index: 601218 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8887. Min Act: -0.0001

Data Index: 869519 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8633. Min Act: -0.0001

Data Index: 1107855 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8245. Min Act: -0.0001

Data Index: 565714 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8887. Min Act: -0.0001

Data Index: 1121990 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 1.2195. Min Range: -1.2195

Max Act: 0.8618. Min Act: -0.0001

Data Index: 121114 (C4 (Web Text))

Max Activating Token Index: 267