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

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

Neuron 736 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1241. Min Range: -3.1241

Max Act: 3.1241. Min Act: -0.0000

Data Index: 406685 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.3273. Min Act: -0.0000

Data Index: 289832 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.1135. Min Act: -0.0000

Data Index: 930204 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.0653. Min Act: -0.0000

Data Index: 76147 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.9570. Min Act: -0.0000

Data Index: 850099 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.1514. Min Act: -0.0000

Data Index: 453564 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.9184. Min Act: -0.0000

Data Index: 1090992 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 3.1241. Min Range: -3.1241

Max Act: 2.0816. Min Act: -0.0000

Data Index: 705433 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.9463. Min Act: -0.0000

Data Index: 926678 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.8229. Min Act: -0.0000

Data Index: 859064 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.8063. Min Act: -0.0000

Data Index: 77674 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.6866. Min Act: -0.0000

Data Index: 61127 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.7621. Min Act: -0.0000

Data Index: 114681 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.7479. Min Act: -0.0000

Data Index: 813422 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.7145. Min Act: -0.0000

Data Index: 117128 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.7082. Min Act: -0.0000

Data Index: 171444 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.7074. Min Act: -0.0000

Data Index: 61475 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.5974. Min Act: -0.0000

Data Index: 486830 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.7078. Min Act: -0.0000

Data Index: 1340576 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.1241. Min Range: -3.1241

Max Act: 1.5489. Min Act: -0.0000

Data Index: 1035917 (C4 (Web Text))

Max Activating Token Index: 710