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

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

Neuron 3600 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.4525. Min Act: -0.0000

Data Index: 744681 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.3556. Min Act: -0.0000

Data Index: 49302 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.2621. Min Act: -0.0001

Data Index: 699068 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.3333. Min Act: -0.0000

Data Index: 866696 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.2937. Min Act: -0.0001

Data Index: 1027508 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.2279. Min Act: -0.0001

Data Index: 1044823 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.2276. Min Act: -0.0001

Data Index: 379545 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1121175 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1804. Min Act: -0.0000

Data Index: 923600 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1496. Min Act: -0.0000

Data Index: 221526 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.2427. Min Act: -0.0001

Data Index: 348411 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1081. Min Act: -0.0001

Data Index: 312708 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1594. Min Act: -0.0001

Data Index: 241512 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1325651 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1758. Min Act: -0.0000

Data Index: 350600 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.0762. Min Act: -0.0000

Data Index: 666591 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.0918. Min Act: -0.0001

Data Index: 139251 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.0685. Min Act: -0.0001

Data Index: 1336142 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.0495. Min Act: -0.0000

Data Index: 368913 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.4525. Min Range: -1.4525

Max Act: 1.1202. Min Act: -0.0000

Data Index: 1145098 (C4 (Web Text))

Max Activating Token Index: 846