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

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

Neuron 76 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: 0.4453. Min Range: -0.4453

Max Act: 0.4453. Min Act: -0.0001

Data Index: 446375 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3561. Min Act: -0.0001

Data Index: 188607 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3599. Min Act: -0.0001

Data Index: 798981 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3502. Min Act: -0.0001

Data Index: 556753 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3341. Min Act: -0.0001

Data Index: 236258 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3215. Min Act: -0.0001

Data Index: 847607 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3328. Min Act: -0.0001

Data Index: 43388 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3306. Min Act: -0.0001

Data Index: 1208620 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3486. Min Act: -0.0001

Data Index: 1329074 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3104. Min Act: -0.0001

Data Index: 1326971 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3365. Min Act: -0.0001

Data Index: 669880 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3271. Min Act: -0.0001

Data Index: 983852 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3094. Min Act: -0.0001

Data Index: 955867 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3278. Min Act: -0.0001

Data Index: 96830 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3371. Min Act: -0.0001

Data Index: 1041124 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3161. Min Act: -0.0001

Data Index: 1359148 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3356. Min Act: -0.0001

Data Index: 441293 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3325. Min Act: -0.0001

Data Index: 232077 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3222. Min Act: -0.0001

Data Index: 899769 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3435. Min Act: -0.0001

Data Index: 878856 (C4 (Web Text))

Max Activating Token Index: 773