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

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

Neuron 2045 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: 0.4960. Min Range: -0.4960

Max Act: 0.4960. Min Act: -0.0000

Data Index: 592497 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.4084. Min Act: -0.0000

Data Index: 515832 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3787. Min Act: -0.0000

Data Index: 228572 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1129107 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3939. Min Act: -0.0000

Data Index: 151298 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1145754 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3656. Min Act: -0.0000

Data Index: 958401 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3540. Min Act: -0.0000

Data Index: 949209 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3749. Min Act: -0.0000

Data Index: 603614 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.3259. Min Act: -0.0000

Data Index: 28796 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1443539 (Python Code)

Max Activating Token Index: 915

Text #11

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2946. Min Act: -0.0000

Data Index: 217846 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2839. Min Act: -0.0000

Data Index: 520880 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2908. Min Act: -0.0000

Data Index: 822632 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2775. Min Act: -0.0000

Data Index: 773385 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1216904 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2694. Min Act: -0.0000

Data Index: 485512 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2569. Min Act: -0.0000

Data Index: 210353 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2651. Min Act: -0.0000

Data Index: 1564346 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 0.4960. Min Range: -0.4960

Max Act: 0.2780. Min Act: -0.0000

Data Index: 335109 (C4 (Web Text))

Max Activating Token Index: 745