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

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

Neuron 2886 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0026. Min Range: -1.0026

Max Act: 1.0026. Min Act: -0.0001

Data Index: 163785 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9254. Min Act: -0.0001

Data Index: 379914 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8113. Min Act: -0.0001

Data Index: 1309845 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9075. Min Act: -0.0001

Data Index: 824065 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8679. Min Act: -0.0001

Data Index: 930937 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8565. Min Act: -0.0001

Data Index: 833117 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8271. Min Act: -0.0001

Data Index: 785181 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8714. Min Act: -0.0001

Data Index: 1337403 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7632. Min Act: -0.0001

Data Index: 292054 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7717. Min Act: -0.0001

Data Index: 437567 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7871. Min Act: -0.0001

Data Index: 1247283 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7573. Min Act: -0.0001

Data Index: 223517 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.6907. Min Act: -0.0001

Data Index: 1196288 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7089. Min Act: -0.0001

Data Index: 836938 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7671. Min Act: -0.0001

Data Index: 1113201 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7927. Min Act: -0.0001

Data Index: 1330403 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8194. Min Act: -0.0001

Data Index: 1194090 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7473. Min Act: -0.0001

Data Index: 24140 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7393. Min Act: -0.0001

Data Index: 237194 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.7567. Min Act: -0.0001

Data Index: 552957 (C4 (Web Text))

Max Activating Token Index: 788