Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3035 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1052628 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5695. Min Act: -0.0001

Data Index: 845598 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5039. Min Act: -0.0000

Data Index: 754994 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.5027. Min Act: -0.0001

Data Index: 985471 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4926. Min Act: -0.0000

Data Index: 100159 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4868. Min Act: -0.0001

Data Index: 1196771 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4930. Min Act: -0.0001

Data Index: 282903 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1184936 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4770. Min Act: -0.0001

Data Index: 395827 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4578. Min Act: -0.0001

Data Index: 526217 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4793. Min Act: -0.0000

Data Index: 418933 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1286093 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4578. Min Act: -0.0001

Data Index: 107106 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4403. Min Act: -0.0001

Data Index: 158404 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4312. Min Act: -0.0001

Data Index: 1163004 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4422. Min Act: -0.0001

Data Index: 447025 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4239. Min Act: -0.0001

Data Index: 526014 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4240. Min Act: -0.0000

Data Index: 116551 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4351. Min Act: -0.0001

Data Index: 640181 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.5695. Min Range: -0.5695

Max Act: 0.4158. Min Act: -0.0001

Data Index: 1159501 (C4 (Web Text))

Max Activating Token Index: 476