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

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

Neuron 3115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3185. Min Act: -0.0001

Data Index: 272540 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2824. Min Act: -0.0001

Data Index: 1136608 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2919. Min Act: -0.0001

Data Index: 409052 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2783. Min Act: -0.0001

Data Index: 907735 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2795. Min Act: -0.0001

Data Index: 957454 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2637. Min Act: -0.0001

Data Index: 576384 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2627. Min Act: -0.0001

Data Index: 462957 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2598. Min Act: -0.0001

Data Index: 844278 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2738. Min Act: -0.0001

Data Index: 191623 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2618. Min Act: -0.0001

Data Index: 228708 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2444. Min Act: -0.0001

Data Index: 808364 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1379579 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2427. Min Act: -0.0000

Data Index: 953506 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2293. Min Act: -0.0001

Data Index: 1165235 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2188. Min Act: -0.0001

Data Index: 831175 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2280. Min Act: -0.0001

Data Index: 737804 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2034. Min Act: -0.0001

Data Index: 945901 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2036. Min Act: -0.0001

Data Index: 245046 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2326. Min Act: -0.0001

Data Index: 507050 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2365. Min Act: -0.0001

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 908