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

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

Neuron 1496 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4875. Min Act: -0.0000

Data Index: 837602 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3986. Min Act: -0.0001

Data Index: 496542 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.4068. Min Act: -0.0000

Data Index: 375294 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3972. Min Act: -0.0000

Data Index: 966526 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3797. Min Act: -0.0000

Data Index: 460559 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3643. Min Act: -0.0001

Data Index: 514613 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3495. Min Act: -0.0001

Data Index: 980826 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1095673 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3470. Min Act: -0.0000

Data Index: 760136 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3369. Min Act: -0.0000

Data Index: 624755 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3351. Min Act: -0.0001

Data Index: 988672 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3349. Min Act: -0.0000

Data Index: 288531 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3233. Min Act: -0.0000

Data Index: 407472 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1053565 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3360. Min Act: -0.0000

Data Index: 838899 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1054412 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3111. Min Act: -0.0000

Data Index: 751403 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3275. Min Act: -0.0001

Data Index: 424304 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3358. Min Act: -0.0001

Data Index: 511353 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.4875. Min Range: -0.4875

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1291715 (C4 (Web Text))

Max Activating Token Index: 442