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

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

Neuron 2445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.9931. Min Act: -0.0000

Data Index: 969077 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.5250. Min Act: -0.0000

Data Index: 409498 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.5903. Min Act: -0.0000

Data Index: 485011 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.4980. Min Act: -0.0000

Data Index: 959292 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.5134. Min Act: -0.0000

Data Index: 151932 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1127980 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3761. Min Act: -0.0000

Data Index: 901965 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.5441. Min Act: -0.0000

Data Index: 296570 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.4691. Min Act: -0.0000

Data Index: 1005591 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.4342. Min Act: -0.0000

Data Index: 864673 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3490. Min Act: -0.0000

Data Index: 158921 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.5126. Min Act: -0.0000

Data Index: 395154 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.5026. Min Act: -0.0000

Data Index: 194057 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3653. Min Act: -0.0000

Data Index: 299581 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1483074 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3717. Min Act: -0.0000

Data Index: 133179 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1270038 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3245. Min Act: -0.0000

Data Index: 565367 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.3163. Min Act: -0.0000

Data Index: 623605 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 1.9931. Min Range: -1.9931

Max Act: 1.2744. Min Act: -0.0000

Data Index: 103427 (C4 (Web Text))

Max Activating Token Index: 900