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

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

Neuron 498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.5464. Min Act: -0.0001

Data Index: 1619911 (Python Code)

Max Activating Token Index: 854

Text #1

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1365997 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3212. Min Act: 0.0001

Data Index: 1488881 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3138. Min Act: 0.0000

Data Index: 1527803 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1548936 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1569052 (Python Code)

Max Activating Token Index: 780

Text #6

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3519. Min Act: -0.0001

Data Index: 1636052 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3003. Min Act: -0.0001

Data Index: 1545677 (Python Code)

Max Activating Token Index: 512

Text #8

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2957. Min Act: 0.0001

Data Index: 1390630 (Python Code)

Max Activating Token Index: 667

Text #9

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1639242 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2958. Min Act: -0.0001

Data Index: 1408177 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2813. Min Act: 0.0000

Data Index: 1401507 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.3009. Min Act: -0.0001

Data Index: 1573693 (Python Code)

Max Activating Token Index: 210

Text #13

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1564512 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2901. Min Act: -0.0001

Data Index: 1454049 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2884. Min Act: -0.0001

Data Index: 1601829 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2861. Min Act: -0.0001

Data Index: 1443142 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2769. Min Act: -0.0001

Data Index: 1569969 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2776. Min Act: 0.0001

Data Index: 1557111 (Python Code)

Max Activating Token Index: 387

Text #19

Max Range: 0.5464. Min Range: -0.5464

Max Act: 0.2822. Min Act: 0.0000

Data Index: 1594324 (Python Code)

Max Activating Token Index: 844