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

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

Neuron 4615 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7859. Min Range: -4.7859

Max Act: 4.7859. Min Act: -0.0000

Data Index: 768679 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.5355. Min Act: -0.0000

Data Index: 1192911 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.9537. Min Act: -0.0000

Data Index: 600087 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.7229. Min Act: -0.0000

Data Index: 1254790 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.6901. Min Act: -0.0000

Data Index: 26789 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.7592. Min Act: -0.0000

Data Index: 1016930 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.5296. Min Act: -0.0000

Data Index: 517772 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.5944. Min Act: -0.0000

Data Index: 1290853 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.3647. Min Act: -0.0000

Data Index: 25342 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.5878. Min Act: -0.0000

Data Index: 65921 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.2179. Min Act: -0.0000

Data Index: 665110 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.3020. Min Act: -0.0000

Data Index: 603603 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.2878. Min Act: -0.0000

Data Index: 834114 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.5311. Min Act: -0.0000

Data Index: 526409 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.8184. Min Act: -0.0000

Data Index: 914886 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 4.7859. Min Range: -4.7859

Max Act: 1.9645. Min Act: -0.0000

Data Index: 494456 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.1892. Min Act: -0.0000

Data Index: 348198 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.1831. Min Act: -0.0000

Data Index: 1273471 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 4.7859. Min Range: -4.7859

Max Act: 1.9803. Min Act: -0.0000

Data Index: 718793 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 4.7859. Min Range: -4.7859

Max Act: 2.0557. Min Act: -0.0000

Data Index: 65405 (C4 (Web Text))

Max Activating Token Index: 265