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

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

Neuron 1899 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: 1.1259. Min Range: -1.1259

Max Act: 1.1259. Min Act: -0.0001

Data Index: 188236 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9840. Min Act: -0.0001

Data Index: 763190 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9755. Min Act: -0.0001

Data Index: 1300860 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9945. Min Act: -0.0001

Data Index: 109880 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9694. Min Act: -0.0001

Data Index: 148073 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8825. Min Act: -0.0001

Data Index: 100225 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.9157. Min Act: -0.0001

Data Index: 1323364 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8280. Min Act: -0.0001

Data Index: 1133948 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8792. Min Act: -0.0001

Data Index: 1091227 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8655. Min Act: -0.0001

Data Index: 803964 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8635. Min Act: -0.0001

Data Index: 378242 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8554. Min Act: -0.0001

Data Index: 721436 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8241. Min Act: -0.0001

Data Index: 715737 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8188. Min Act: -0.0001

Data Index: 301006 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8414. Min Act: -0.0001

Data Index: 1084545 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.7969. Min Act: -0.0001

Data Index: 271309 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1128433 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8094. Min Act: -0.0001

Data Index: 426788 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.7708. Min Act: -0.0001

Data Index: 1096694 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.1259. Min Range: -1.1259

Max Act: 0.8138. Min Act: -0.0001

Data Index: 77561 (C4 (Web Text))

Max Activating Token Index: 470