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

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

Neuron 3805 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: 0.4318. Min Range: -0.4318

Max Act: 0.4318. Min Act: -0.0001

Data Index: 387561 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3363. Min Act: -0.0001

Data Index: 695392 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3342. Min Act: -0.0001

Data Index: 415893 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3000. Min Act: -0.0001

Data Index: 346229 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1209407 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3352. Min Act: -0.0001

Data Index: 67020 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3040. Min Act: -0.0001

Data Index: 993857 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2916. Min Act: -0.0000

Data Index: 520829 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.3022. Min Act: -0.0001

Data Index: 897198 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2970. Min Act: -0.0001

Data Index: 1005247 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2807. Min Act: -0.0001

Data Index: 429441 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2864. Min Act: -0.0001

Data Index: 1266311 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2842. Min Act: -0.0001

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2634. Min Act: -0.0000

Data Index: 591294 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2610. Min Act: -0.0001

Data Index: 271755 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1255483 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2666. Min Act: -0.0001

Data Index: 89760 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2810. Min Act: -0.0001

Data Index: 80531 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1069829 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.4318. Min Range: -0.4318

Max Act: 0.2538. Min Act: -0.0001

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 633