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

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

Neuron 717 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: 1.6058. Min Range: -1.6058

Max Act: 1.6058. Min Act: -0.0000

Data Index: 186125 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1300868 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.2972. Min Act: -0.0000

Data Index: 997211 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.2240. Min Act: -0.0000

Data Index: 937409 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.3099. Min Act: -0.0000

Data Index: 291534 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1128056 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1906. Min Act: -0.0000

Data Index: 356372 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1501. Min Act: -0.0000

Data Index: 16810 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1521. Min Act: -0.0000

Data Index: 753197 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1298619 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0204. Min Act: -0.0000

Data Index: 396051 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9934. Min Act: -0.0000

Data Index: 955230 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9862. Min Act: -0.0000

Data Index: 460951 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9861. Min Act: -0.0000

Data Index: 121282 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1055. Min Act: -0.0000

Data Index: 64969 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.1113. Min Act: -0.0000

Data Index: 48511 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1229421 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9924. Min Act: -0.0000

Data Index: 877324 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.6058. Min Range: -1.6058

Max Act: 1.0432. Min Act: -0.0000

Data Index: 371062 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.6058. Min Range: -1.6058

Max Act: 0.9227. Min Act: -0.0000

Data Index: 616889 (C4 (Web Text))

Max Activating Token Index: 188