Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.7008. Min Act: -0.0001

Data Index: 1076008 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.4852. Min Act: -0.0000

Data Index: 711606 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.4954. Min Act: -0.0000

Data Index: 1180138 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.3958. Min Act: -0.0001

Data Index: 860779 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.6137. Min Act: -0.0000

Data Index: 705578 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.4442. Min Act: -0.0001

Data Index: 105208 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5201. Min Act: -0.0001

Data Index: 786405 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.3840. Min Act: -0.0000

Data Index: 381760 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.3211. Min Act: -0.0001

Data Index: 479171 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.4553. Min Act: -0.0000

Data Index: 932989 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1084000 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.3624. Min Act: -0.0001

Data Index: 700918 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.2681. Min Act: -0.0001

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.2910. Min Act: -0.0001

Data Index: 159530 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.2520. Min Act: -0.0001

Data Index: 983034 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.2193. Min Act: -0.0000

Data Index: 614837 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.2094. Min Act: -0.0001

Data Index: 1185332 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.1259. Min Act: -0.0001

Data Index: 696266 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.1660. Min Act: -0.0000

Data Index: 945683 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.1856. Min Act: -0.0001

Data Index: 1184131 (C4 (Web Text))

Max Activating Token Index: 811