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

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

Neuron 6102 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: 2.4091. Min Range: -2.4091

Max Act: 2.4091. Min Act: -0.0001

Data Index: 172484 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.3728. Min Act: -0.0000

Data Index: 368064 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.0672. Min Act: -0.0000

Data Index: 1326231 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.0593. Min Act: -0.0001

Data Index: 660823 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.0563. Min Act: -0.0000

Data Index: 1358801 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.1476. Min Act: -0.0001

Data Index: 1209446 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.1168. Min Act: -0.0000

Data Index: 662525 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.0262. Min Act: -0.0000

Data Index: 1330104 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.9850. Min Act: -0.0001

Data Index: 11478 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.9141. Min Act: -0.0000

Data Index: 1330083 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.1068. Min Act: -0.0000

Data Index: 153343 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.9748. Min Act: -0.0001

Data Index: 79692 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.9886. Min Act: -0.0001

Data Index: 785962 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.8506. Min Act: -0.0000

Data Index: 366481 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.9356. Min Act: -0.0001

Data Index: 1201118 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.0142. Min Act: -0.0001

Data Index: 267829 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 2.4091. Min Range: -2.4091

Max Act: 2.0195. Min Act: -0.0000

Data Index: 370558 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.8983. Min Act: -0.0001

Data Index: 510022 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.7911. Min Act: -0.0000

Data Index: 1075490 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 2.4091. Min Range: -2.4091

Max Act: 1.8431. Min Act: -0.0001

Data Index: 768227 (C4 (Web Text))

Max Activating Token Index: 207