Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 690 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6464. Min Range: -5.6464

Max Act: 5.6464. Min Act: -0.0000

Data Index: 766864 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.9745. Min Act: -0.0000

Data Index: 489227 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.9950. Min Act: -0.0000

Data Index: 320330 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.8506. Min Act: -0.0001

Data Index: 310328 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 5.6464. Min Range: -5.6464

Max Act: 5.1569. Min Act: -0.0000

Data Index: 589820 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.7901. Min Act: -0.0000

Data Index: 1288241 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.9850. Min Act: -0.0000

Data Index: 1075144 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.5194. Min Act: -0.0001

Data Index: 998821 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.3780. Min Act: -0.0000

Data Index: 1110404 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.1357. Min Act: -0.0000

Data Index: 392591 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.2199. Min Act: -0.0000

Data Index: 89026 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 5.6464. Min Range: -5.6464

Max Act: 4.0361. Min Act: -0.0000

Data Index: 519140 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 5.6464. Min Range: -5.6464

Max Act: 3.4441. Min Act: -0.0000

Data Index: 468407 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 5.6464. Min Range: -5.6464

Max Act: 3.3433. Min Act: -0.0000

Data Index: 1075090 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 5.6464. Min Range: -5.6464

Max Act: 3.2182. Min Act: -0.0000

Data Index: 1312539 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 5.6464. Min Range: -5.6464

Max Act: 3.0867. Min Act: -0.0000

Data Index: 862393 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 5.6464. Min Range: -5.6464

Max Act: 3.1215. Min Act: -0.0000

Data Index: 1313100 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 5.6464. Min Range: -5.6464

Max Act: 2.9981. Min Act: -0.0000

Data Index: 784453 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 5.6464. Min Range: -5.6464

Max Act: 2.9632. Min Act: -0.0001

Data Index: 445617 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 5.6464. Min Range: -5.6464

Max Act: 2.9650. Min Act: -0.0000

Data Index: 316396 (C4 (Web Text))

Max Activating Token Index: 705