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

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

Neuron 1100 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: 2.0067. Min Range: -2.0067

Max Act: 2.0067. Min Act: -0.0000

Data Index: 827266 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.8858. Min Act: -0.0000

Data Index: 181233 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.8001. Min Act: -0.0001

Data Index: 1274280 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.4960. Min Act: -0.0001

Data Index: 741180 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.2057. Min Act: -0.0000

Data Index: 637997 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.4068. Min Act: -0.0000

Data Index: 22500 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.4700. Min Act: -0.0001

Data Index: 105793 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.4639. Min Act: -0.0000

Data Index: 904449 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.3656. Min Act: -0.0001

Data Index: 127626 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.2138. Min Act: -0.0001

Data Index: 780970 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.3754. Min Act: -0.0001

Data Index: 981296 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.3275. Min Act: -0.0000

Data Index: 220724 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.2096. Min Act: -0.0001

Data Index: 645263 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1088758 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.3100. Min Act: -0.0000

Data Index: 192346 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.3023. Min Act: -0.0000

Data Index: 104176 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.2148. Min Act: -0.0001

Data Index: 459254 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.2761. Min Act: -0.0001

Data Index: 598692 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1074798 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.0067. Min Range: -2.0067

Max Act: 1.2429. Min Act: -0.0000

Data Index: 363930 (C4 (Web Text))

Max Activating Token Index: 44