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

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

Neuron 5316 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.9605. Min Act: -0.0002

Data Index: 675481 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.6138. Min Act: -0.0002

Data Index: 166230 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5669. Min Act: -0.0002

Data Index: 358140 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4729. Min Act: -0.0002

Data Index: 669118 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.5160. Min Act: -0.0002

Data Index: 632733 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4387. Min Act: -0.0002

Data Index: 1184781 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.4680. Min Act: -0.0002

Data Index: 926672 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3922. Min Act: -0.0002

Data Index: 1124828 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3958. Min Act: -0.0002

Data Index: 127850 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3958. Min Act: -0.0002

Data Index: 888019 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3617. Min Act: -0.0002

Data Index: 389977 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3760. Min Act: -0.0002

Data Index: 1169590 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3539. Min Act: -0.0002

Data Index: 703864 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3465. Min Act: -0.0002

Data Index: 1135345 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3481. Min Act: -0.0002

Data Index: 321149 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3771. Min Act: -0.0002

Data Index: 1262485 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3562. Min Act: -0.0002

Data Index: 134103 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3599. Min Act: -0.0002

Data Index: 578313 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3499. Min Act: -0.0002

Data Index: 559327 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.9605. Min Range: -1.9605

Max Act: 1.3688. Min Act: -0.0002

Data Index: 814741 (C4 (Web Text))

Max Activating Token Index: 316