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

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

Neuron 2958 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0003

Data Index: 1184411 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1299. Min Act: -0.0003

Data Index: 864660 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1297. Min Act: -0.0003

Data Index: 800885 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1278. Min Act: -0.0003

Data Index: 1059563 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1173. Min Act: -0.0003

Data Index: 851350 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1170. Min Act: -0.0003

Data Index: 1267263 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1081. Min Act: -0.0003

Data Index: 693526 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1078. Min Act: -0.0003

Data Index: 126246 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1113. Min Act: -0.0003

Data Index: 365910 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1063. Min Act: -0.0003

Data Index: 717869 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1061. Min Act: -0.0003

Data Index: 1112145 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1056. Min Act: -0.0003

Data Index: 792634 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1081. Min Act: -0.0003

Data Index: 312622 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1026. Min Act: -0.0003

Data Index: 129373 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1005. Min Act: -0.0003

Data Index: 396761 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0967. Min Act: -0.0003

Data Index: 591980 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0983. Min Act: -0.0003

Data Index: 469446 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0983. Min Act: -0.0002

Data Index: 538351 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0974. Min Act: -0.0003

Data Index: 303615 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0969. Min Act: -0.0003

Data Index: 300183 (C4 (Web Text))

Max Activating Token Index: 178