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

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

Neuron 4838 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4531. Min Act: -0.0001

Data Index: 1338767 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.4932. Min Act: -0.0001

Data Index: 1241936 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0083. Min Act: -0.0001

Data Index: 797559 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0661. Min Act: -0.0001

Data Index: 1203692 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.1378. Min Act: -0.0001

Data Index: 263335 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.1128. Min Act: -0.0001

Data Index: 1354593 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.1180. Min Act: -0.0001

Data Index: 1056224 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.1285. Min Act: -0.0001

Data Index: 768156 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0180. Min Act: -0.0001

Data Index: 1058600 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0140. Min Act: -0.0001

Data Index: 1026588 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0317. Min Act: -0.0001

Data Index: 515963 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9107. Min Act: -0.0001

Data Index: 43931 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9522. Min Act: -0.0001

Data Index: 819936 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9853. Min Act: -0.0001

Data Index: 257974 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9692. Min Act: -0.0001

Data Index: 781129 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9415. Min Act: -0.0001

Data Index: 1122994 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9219. Min Act: -0.0001

Data Index: 818099 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9535. Min Act: -0.0001

Data Index: 158268 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 1.4932. Min Range: -1.4932

Max Act: 0.9549. Min Act: -0.0001

Data Index: 708052 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.4932. Min Range: -1.4932

Max Act: 1.0456. Min Act: -0.0001

Data Index: 193084 (C4 (Web Text))

Max Activating Token Index: 828