Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2986 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.3381. Min Range: -2.3381

Max Act: 2.3381. Min Act: -0.0000

Data Index: 161963 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.9232. Min Act: -0.0001

Data Index: 717984 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.6837. Min Act: -0.0000

Data Index: 995301 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.5784. Min Act: -0.0001

Data Index: 1259291 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.6025. Min Act: -0.0001

Data Index: 394347 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.4132. Min Act: -0.0001

Data Index: 209847 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.5126. Min Act: -0.0001

Data Index: 697822 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.3547. Min Act: -0.0001

Data Index: 188817 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.3561. Min Act: -0.0000

Data Index: 700763 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.4297. Min Act: -0.0001

Data Index: 722532 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.4188. Min Act: -0.0001

Data Index: 471309 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.4015. Min Act: -0.0001

Data Index: 1501325 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.2662. Min Act: -0.0001

Data Index: 534208 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.2778. Min Act: -0.0001

Data Index: 1516006 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.2312. Min Act: -0.0001

Data Index: 1298512 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.2280. Min Act: -0.0001

Data Index: 2826 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.2762. Min Act: -0.0001

Data Index: 780168 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 2.3381. Min Range: -2.3381

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1048267 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.1390. Min Act: -0.0001

Data Index: 273789 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 2.3381. Min Range: -2.3381

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1033549 (C4 (Web Text))

Max Activating Token Index: 717