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

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

Neuron 4138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0596. Min Act: -0.0002

Data Index: 317184 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0540. Min Act: -0.0002

Data Index: 790958 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0540. Min Act: -0.0002

Data Index: 797422 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0499. Min Act: -0.0002

Data Index: 876352 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0481. Min Act: -0.0002

Data Index: 593408 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0512. Min Act: -0.0002

Data Index: 206025 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0455. Min Act: -0.0002

Data Index: 757815 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0444. Min Act: -0.0002

Data Index: 305641 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0443. Min Act: -0.0002

Data Index: 73101 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0436. Min Act: -0.0002

Data Index: 735654 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1025517 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0410. Min Act: -0.0002

Data Index: 551733 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1327114 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1051227 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0400. Min Act: -0.0002

Data Index: 442726 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0448. Min Act: -0.0002

Data Index: 881620 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1271573 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0388. Min Act: -0.0002

Data Index: 360097 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0386. Min Act: -0.0002

Data Index: 714118 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0382. Min Act: -0.0002

Data Index: 672893 (C4 (Web Text))

Max Activating Token Index: 635