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

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

Neuron 4149 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4142. Min Act: -0.0000

Data Index: 636022 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.4146. Min Act: -0.0001

Data Index: 975926 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3861. Min Act: -0.0001

Data Index: 661503 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3781. Min Act: -0.0000

Data Index: 695577 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3491. Min Act: -0.0000

Data Index: 80051 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3609. Min Act: -0.0000

Data Index: 121021 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3256. Min Act: -0.0000

Data Index: 925157 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3037. Min Act: -0.0001

Data Index: 716384 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1251068 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1096234 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1264015 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3082. Min Act: -0.0000

Data Index: 223287 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.3301. Min Act: -0.0001

Data Index: 1005759 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2931. Min Act: -0.0000

Data Index: 544079 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2696. Min Act: -0.0000

Data Index: 864634 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2472. Min Act: -0.0000

Data Index: 749617 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1477111 (Python Code)

Max Activating Token Index: 799

Text #17

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1297622 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2906. Min Act: -0.0001

Data Index: 1231640 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.4146. Min Range: -0.4146

Max Act: 0.2977. Min Act: -0.0000

Data Index: 746536 (C4 (Web Text))

Max Activating Token Index: 909