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

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

Neuron 3555 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: 5.1224. Min Range: -5.1224

Max Act: 5.1224. Min Act: -0.0000

Data Index: 784739 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.6686. Min Act: -0.0000

Data Index: 712304 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.4396. Min Act: -0.0000

Data Index: 1188088 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.3559. Min Act: -0.0000

Data Index: 860545 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.2381. Min Act: -0.0000

Data Index: 1353029 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.2155. Min Act: -0.0000

Data Index: 230561 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.3409. Min Act: -0.0000

Data Index: 693202 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.2262. Min Act: -0.0000

Data Index: 271470 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.8268. Min Act: -0.0001

Data Index: 446177 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.0536. Min Act: -0.0000

Data Index: 251908 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.0155. Min Act: -0.0001

Data Index: 522516 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 5.1224. Min Range: -5.1224

Max Act: 4.0039. Min Act: -0.0001

Data Index: 1337458 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.7991. Min Act: -0.0000

Data Index: 1125747 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.9127. Min Act: -0.0000

Data Index: 431693 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.9026. Min Act: -0.0000

Data Index: 1168052 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.8638. Min Act: -0.0000

Data Index: 967063 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.7849. Min Act: -0.0000

Data Index: 1324804 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.7061. Min Act: -0.0000

Data Index: 972916 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.6596. Min Act: -0.0001

Data Index: 575529 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 5.1224. Min Range: -5.1224

Max Act: 3.7837. Min Act: -0.0000

Data Index: 260611 (C4 (Web Text))

Max Activating Token Index: 216