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

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

Neuron 2923 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0196. Min Range: -1.0196

Max Act: 1.0196. Min Act: -0.0001

Data Index: 177451 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.8886. Min Act: -0.0001

Data Index: 1189556 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.9143. Min Act: -0.0001

Data Index: 1223636 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.9575. Min Act: -0.0001

Data Index: 905703 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.8806. Min Act: -0.0001

Data Index: 295506 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6934. Min Act: -0.0001

Data Index: 732083 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.7956. Min Act: -0.0001

Data Index: 457569 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.7577. Min Act: -0.0001

Data Index: 627811 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.8278. Min Act: -0.0001

Data Index: 90924 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1214543 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.7403. Min Act: -0.0001

Data Index: 835579 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6595. Min Act: -0.0001

Data Index: 1243452 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6812. Min Act: -0.0001

Data Index: 420557 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.7155. Min Act: -0.0001

Data Index: 414084 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6951. Min Act: -0.0001

Data Index: 1047112 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1004745 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6538. Min Act: -0.0001

Data Index: 174976 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6505. Min Act: -0.0001

Data Index: 325695 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6660. Min Act: -0.0001

Data Index: 1030099 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.0196. Min Range: -1.0196

Max Act: 0.6390. Min Act: -0.0001

Data Index: 1007974 (C4 (Web Text))

Max Activating Token Index: 858