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

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

Neuron 4450 in Layer 0

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: 0.3340. Min Range: -0.3340

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1127328 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3063. Min Act: -0.0001

Data Index: 50753 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2851. Min Act: -0.0001

Data Index: 661449 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2747. Min Act: -0.0001

Data Index: 202274 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2718. Min Act: -0.0001

Data Index: 540645 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2700. Min Act: -0.0001

Data Index: 390611 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2691. Min Act: -0.0001

Data Index: 190801 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1225654 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2664. Min Act: -0.0001

Data Index: 1011502 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2628. Min Act: -0.0001

Data Index: 33624 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2643. Min Act: -0.0001

Data Index: 772727 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1020469 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2556. Min Act: -0.0001

Data Index: 364242 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2553. Min Act: -0.0001

Data Index: 709510 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2625. Min Act: -0.0001

Data Index: 13403 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2548. Min Act: -0.0001

Data Index: 1112765 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2573. Min Act: -0.0001

Data Index: 320729 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2521. Min Act: -0.0001

Data Index: 585213 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2546. Min Act: -0.0001

Data Index: 121290 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2495. Min Act: -0.0001

Data Index: 1357249 (C4 (Web Text))

Max Activating Token Index: 92