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

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

Neuron 100 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.9137. Min Act: -0.0000

Data Index: 185683 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1178581 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8516. Min Act: -0.0000

Data Index: 440054 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1040367 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7902. Min Act: -0.0000

Data Index: 836002 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7909. Min Act: -0.0000

Data Index: 425113 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7716. Min Act: -0.0000

Data Index: 476129 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7377. Min Act: -0.0000

Data Index: 1255890 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7236. Min Act: -0.0000

Data Index: 927603 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7188. Min Act: -0.0000

Data Index: 1048905 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6952. Min Act: -0.0000

Data Index: 236524 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1156167 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7138. Min Act: -0.0000

Data Index: 891110 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1136292 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6761. Min Act: 0.0000

Data Index: 497059 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6624. Min Act: -0.0000

Data Index: 760315 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1286926 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6689. Min Act: -0.0000

Data Index: 595570 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6629. Min Act: -0.0000

Data Index: 825455 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.9137. Min Range: -0.9137

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1079595 (C4 (Web Text))

Max Activating Token Index: 113