Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.3065. Min Act: -0.0001

Data Index: 594952 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.3244. Min Act: -0.0001

Data Index: 309746 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.3006. Min Act: -0.0001

Data Index: 334945 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2717. Min Act: -0.0001

Data Index: 577152 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2795. Min Act: -0.0001

Data Index: 570445 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.3033. Min Act: -0.0001

Data Index: 11033 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2486. Min Act: -0.0001

Data Index: 1506106 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2705. Min Act: -0.0001

Data Index: 114910 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2573. Min Act: -0.0001

Data Index: 78906 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2386. Min Act: -0.0001

Data Index: 275770 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1255838 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1423053 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1059326 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2422. Min Act: -0.0001

Data Index: 1089808 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2441. Min Act: -0.0001

Data Index: 844802 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2395. Min Act: -0.0001

Data Index: 956702 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2661. Min Act: -0.0001

Data Index: 275093 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2333. Min Act: -0.0001

Data Index: 268701 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2192. Min Act: -0.0001

Data Index: 312828 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.3244. Min Range: -0.3244

Max Act: 0.2519. Min Act: -0.0001

Data Index: 228589 (C4 (Web Text))

Max Activating Token Index: 876