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

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

Neuron 5658 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2964. Min Range: -3.2964

Max Act: 3.2964. Min Act: -0.0000

Data Index: 1054131 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.8293. Min Act: -0.0000

Data Index: 234112 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.7456. Min Act: -0.0000

Data Index: 1084700 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.8595. Min Act: -0.0000

Data Index: 751014 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.6522. Min Act: -0.0000

Data Index: 1213238 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.4335. Min Act: -0.0000

Data Index: 318317 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.2396. Min Act: -0.0000

Data Index: 667720 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.4536. Min Act: -0.0000

Data Index: 88220 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.3578. Min Act: -0.0000

Data Index: 258615 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.2294. Min Act: -0.0000

Data Index: 615161 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.1354. Min Act: -0.0000

Data Index: 108574 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.2530. Min Act: -0.0000

Data Index: 712757 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.3715. Min Act: -0.0000

Data Index: 850732 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.1865. Min Act: -0.0000

Data Index: 1030520 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.0545. Min Act: -0.0000

Data Index: 126807 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.0755. Min Act: -0.0000

Data Index: 259747 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.0430. Min Act: -0.0000

Data Index: 1316733 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.2964. Min Range: -3.2964

Max Act: 2.0199. Min Act: -0.0000

Data Index: 731241 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 3.2964. Min Range: -3.2964

Max Act: 1.9484. Min Act: -0.0000

Data Index: 4227 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 3.2964. Min Range: -3.2964

Max Act: 1.9839. Min Act: -0.0000

Data Index: 1331440 (C4 (Web Text))

Max Activating Token Index: 256