Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 856 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.3152. Min Act: -0.0001

Data Index: 1200236 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2631. Min Act: -0.0001

Data Index: 864868 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2536. Min Act: -0.0001

Data Index: 792047 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2593. Min Act: -0.0001

Data Index: 675883 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2495. Min Act: -0.0001

Data Index: 662001 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2491. Min Act: -0.0001

Data Index: 1201870 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2419. Min Act: -0.0001

Data Index: 906375 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1125985 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2394. Min Act: -0.0001

Data Index: 963543 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2372. Min Act: -0.0001

Data Index: 120236 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2204. Min Act: -0.0001

Data Index: 1072914 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2261. Min Act: -0.0001

Data Index: 110687 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2240. Min Act: -0.0001

Data Index: 338707 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2411. Min Act: -0.0001

Data Index: 615641 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2229. Min Act: -0.0001

Data Index: 52615 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1290221 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2314. Min Act: -0.0001

Data Index: 258709 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2368. Min Act: -0.0001

Data Index: 784739 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2205. Min Act: -0.0001

Data Index: 525918 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.3152. Min Range: -0.3152

Max Act: 0.2189. Min Act: -0.0001

Data Index: 139375 (C4 (Web Text))

Max Activating Token Index: 814