Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4951 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.3422. Min Act: -0.0000

Data Index: 370034 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2925. Min Act: -0.0000

Data Index: 207922 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1098219 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2721. Min Act: -0.0000

Data Index: 783599 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2567. Min Act: -0.0000

Data Index: 730027 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2520. Min Act: -0.0000

Data Index: 422233 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2456. Min Act: -0.0000

Data Index: 107356 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2483. Min Act: -0.0000

Data Index: 596801 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2436. Min Act: -0.0000

Data Index: 717225 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2465. Min Act: 0.0001

Data Index: 885873 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2283. Min Act: -0.0000

Data Index: 359614 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2269. Min Act: -0.0000

Data Index: 692135 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2264. Min Act: -0.0000

Data Index: 625933 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1068255 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2310. Min Act: -0.0000

Data Index: 868664 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1273139 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2396. Min Act: -0.0000

Data Index: 914957 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2155. Min Act: -0.0000

Data Index: 764686 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1305152 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.3422. Min Range: -0.3422

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1076337 (C4 (Web Text))

Max Activating Token Index: 600