Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1653 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4972. Min Act: -0.0001

Data Index: 921999 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.6207. Min Act: -0.0001

Data Index: 103739 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4915. Min Act: -0.0001

Data Index: 506940 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.5894. Min Act: -0.0001

Data Index: 1161039 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4993. Min Act: -0.0001

Data Index: 993440 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.5601. Min Act: -0.0001

Data Index: 265976 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3837. Min Act: -0.0001

Data Index: 452449 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4414. Min Act: -0.0001

Data Index: 956507 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4117. Min Act: -0.0000

Data Index: 632987 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3205. Min Act: -0.0001

Data Index: 976616 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3654. Min Act: -0.0001

Data Index: 286660 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3969. Min Act: -0.0001

Data Index: 378542 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3417. Min Act: -0.0001

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3547. Min Act: -0.0001

Data Index: 930109 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.4988. Min Act: -0.0001

Data Index: 826112 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3710. Min Act: -0.0001

Data Index: 832107 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3322. Min Act: -0.0001

Data Index: 878133 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3354. Min Act: -0.0001

Data Index: 102190 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3834. Min Act: -0.0001

Data Index: 1065492 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.6207. Min Range: -1.6207

Max Act: 1.3403. Min Act: -0.0001

Data Index: 102055 (C4 (Web Text))

Max Activating Token Index: 888