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

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

Neuron 3271 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.8497. Min Act: -0.0001

Data Index: 508951 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7654. Min Act: -0.0001

Data Index: 1067547 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7376. Min Act: -0.0001

Data Index: 518952 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7076. Min Act: -0.0001

Data Index: 152443 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.7148. Min Act: -0.0001

Data Index: 1358456 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6433. Min Act: -0.0001

Data Index: 1250697 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6599. Min Act: -0.0001

Data Index: 1014555 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6319. Min Act: -0.0001

Data Index: 548415 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5800. Min Act: -0.0001

Data Index: 1166209 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6269. Min Act: -0.0001

Data Index: 850418 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6361. Min Act: -0.0001

Data Index: 608512 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6345. Min Act: -0.0001

Data Index: 554861 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5890. Min Act: -0.0001

Data Index: 1254540 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6237. Min Act: -0.0001

Data Index: 864680 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5965. Min Act: -0.0001

Data Index: 732183 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6252. Min Act: -0.0001

Data Index: 642813 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.5726. Min Act: -0.0000

Data Index: 273200 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6067. Min Act: -0.0001

Data Index: 239069 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6111. Min Act: -0.0001

Data Index: 1084358 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.8497. Min Range: -0.8497

Max Act: 0.6311. Min Act: -0.0001

Data Index: 298684 (C4 (Web Text))

Max Activating Token Index: 233