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

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

Neuron 949 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: 0.3292. Min Range: -0.3292

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1549424 (Python Code)

Max Activating Token Index: 620

Text #1

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1621999 (Python Code)

Max Activating Token Index: 643

Text #2

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3069. Min Act: -0.0001

Data Index: 1505224 (Python Code)

Max Activating Token Index: 505

Text #3

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1604670 (Python Code)

Max Activating Token Index: 448

Text #4

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3083. Min Act: -0.0001

Data Index: 1400666 (Python Code)

Max Activating Token Index: 596

Text #5

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3078. Min Act: -0.0001

Data Index: 1584721 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1443204 (Python Code)

Max Activating Token Index: 758

Text #7

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1394297 (Python Code)

Max Activating Token Index: 904

Text #8

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3027. Min Act: -0.0001

Data Index: 1510417 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.3012. Min Act: -0.0001

Data Index: 1448119 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1553006 (Python Code)

Max Activating Token Index: 603

Text #11

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2808. Min Act: -0.0001

Data Index: 1538965 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2799. Min Act: -0.0001

Data Index: 1561204 (Python Code)

Max Activating Token Index: 536

Text #13

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2818. Min Act: -0.0001

Data Index: 1563933 (Python Code)

Max Activating Token Index: 263

Text #14

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2782. Min Act: -0.0001

Data Index: 1645314 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2842. Min Act: -0.0001

Data Index: 1435853 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1656447 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2757. Min Act: -0.0001

Data Index: 1497234 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2603. Min Act: -0.0001

Data Index: 1447109 (Python Code)

Max Activating Token Index: 348

Text #19

Max Range: 0.3292. Min Range: -0.3292

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1594565 (Python Code)

Max Activating Token Index: 291