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

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

Neuron 4652 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6532. Min Range: -2.6532

Max Act: 2.6532. Min Act: -0.0000

Data Index: 754117 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 2.6532. Min Range: -2.6532

Max Act: 2.4830. Min Act: -0.0000

Data Index: 899296 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 2.6532. Min Range: -2.6532

Max Act: 2.3470. Min Act: -0.0000

Data Index: 162297 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 2.6532. Min Range: -2.6532

Max Act: 2.1009. Min Act: -0.0000

Data Index: 85898 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 2.6532. Min Range: -2.6532

Max Act: 2.1386. Min Act: -0.0000

Data Index: 653747 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 2.6532. Min Range: -2.6532

Max Act: 2.0193. Min Act: -0.0000

Data Index: 787520 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 2.6532. Min Range: -2.6532

Max Act: 2.0186. Min Act: -0.0000

Data Index: 335801 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.8938. Min Act: -0.0000

Data Index: 1291464 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.8486. Min Act: -0.0000

Data Index: 1356415 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.7361. Min Act: -0.0000

Data Index: 1080499 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1118804 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.7678. Min Act: -0.0000

Data Index: 840618 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.7546. Min Act: -0.0000

Data Index: 419096 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.7654. Min Act: -0.0000

Data Index: 558454 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.8308. Min Act: -0.0000

Data Index: 530043 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.6370. Min Act: -0.0000

Data Index: 741465 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.7217. Min Act: -0.0000

Data Index: 683229 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.6628. Min Act: -0.0000

Data Index: 316224 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.7539. Min Act: -0.0000

Data Index: 1215180 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 2.6532. Min Range: -2.6532

Max Act: 1.6453. Min Act: -0.0000

Data Index: 296192 (C4 (Web Text))

Max Activating Token Index: 929