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

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

Neuron 2582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1486596 (Python Code)

Max Activating Token Index: 198

Text #1

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1369697 (Python Code)

Max Activating Token Index: 180

Text #2

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1421906 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1581168 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1536772 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1619118 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1486439 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1516295 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1651067 (Python Code)

Max Activating Token Index: 84

Text #9

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1594209 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1632333 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1377107 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1437681 (Python Code)

Max Activating Token Index: 167

Text #13

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1402986 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1560432 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1367396 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1563880 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1635428 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1483694 (Python Code)

Max Activating Token Index: 120

Text #19

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1399003 (Python Code)

Max Activating Token Index: 38