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

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

Neuron 5559 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1134. Min Range: -4.1134

Max Act: 4.1134. Min Act: -0.0000

Data Index: 1013513 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.8038. Min Act: -0.0000

Data Index: 125563 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.7386. Min Act: -0.0001

Data Index: 1313367 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3216. Min Act: -0.0000

Data Index: 1205989 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.4516. Min Act: -0.0001

Data Index: 1057999 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.7643. Min Act: -0.0001

Data Index: 1310588 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3113. Min Act: -0.0001

Data Index: 837882 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.5314. Min Act: -0.0000

Data Index: 833027 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3583. Min Act: -0.0001

Data Index: 1286228 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3537. Min Act: -0.0001

Data Index: 697120 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.5872. Min Act: -0.0000

Data Index: 1112015 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.5449. Min Act: -0.0001

Data Index: 756473 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3991. Min Act: -0.0000

Data Index: 622634 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3984. Min Act: -0.0000

Data Index: 563070 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3970. Min Act: -0.0001

Data Index: 953016 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.3843. Min Act: -0.0001

Data Index: 592489 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.5358. Min Act: -0.0001

Data Index: 1323715 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.1499. Min Act: -0.0000

Data Index: 493067 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 4.1134. Min Range: -4.1134

Max Act: 2.8918. Min Act: -0.0001

Data Index: 108023 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 4.1134. Min Range: -4.1134

Max Act: 3.1509. Min Act: -0.0000

Data Index: 959614 (C4 (Web Text))

Max Activating Token Index: 615