Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2030 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.5516. Min Range: -4.5516

Max Act: 4.5516. Min Act: -0.0000

Data Index: 857359 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 4.5516. Min Range: -4.5516

Max Act: 3.3876. Min Act: -0.0000

Data Index: 154778 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 4.5516. Min Range: -4.5516

Max Act: 3.0182. Min Act: -0.0000

Data Index: 816064 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 4.5516. Min Range: -4.5516

Max Act: 3.0178. Min Act: -0.0000

Data Index: 1147335 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 4.5516. Min Range: -4.5516

Max Act: 3.0638. Min Act: -0.0000

Data Index: 1159943 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.9967. Min Act: -0.0000

Data Index: 356210 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.9107. Min Act: -0.0000

Data Index: 892977 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.8843. Min Act: -0.0000

Data Index: 1046705 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.5632. Min Act: -0.0000

Data Index: 127379 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.6831. Min Act: -0.0000

Data Index: 1331242 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.6262. Min Act: -0.0000

Data Index: 425811 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.6200. Min Act: -0.0000

Data Index: 478881 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.6035. Min Act: -0.0000

Data Index: 1045899 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.5573. Min Act: -0.0000

Data Index: 506048 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.5062. Min Act: -0.0000

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.3796. Min Act: -0.0000

Data Index: 614402 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.3341. Min Act: -0.0000

Data Index: 1102274 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.4559. Min Act: -0.0000

Data Index: 380463 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.4354. Min Act: -0.0000

Data Index: 1208519 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 4.5516. Min Range: -4.5516

Max Act: 2.4409. Min Act: -0.0000

Data Index: 441726 (C4 (Web Text))

Max Activating Token Index: 766