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

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

Neuron 3120 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: 4.3884. Min Range: -4.3884

Max Act: 3.6588. Min Act: -0.0001

Data Index: 2321 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 4.3884. Min Range: -4.3884

Max Act: 4.3884. Min Act: -0.0000

Data Index: 714957 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 4.3884. Min Range: -4.3884

Max Act: 3.6147. Min Act: -0.0001

Data Index: 238467 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 4.3884. Min Range: -4.3884

Max Act: 3.6599. Min Act: -0.0000

Data Index: 867548 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 4.3884. Min Range: -4.3884

Max Act: 3.4562. Min Act: -0.0000

Data Index: 134421 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.9547. Min Act: -0.0000

Data Index: 1041503 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.9974. Min Act: -0.0000

Data Index: 825960 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 4.3884. Min Range: -4.3884

Max Act: 3.0365. Min Act: -0.0000

Data Index: 210492 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.8000. Min Act: -0.0000

Data Index: 1126974 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.7607. Min Act: -0.0000

Data Index: 1105667 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.6230. Min Act: -0.0000

Data Index: 606316 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.5138. Min Act: -0.0000

Data Index: 414759 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.3975. Min Act: -0.0000

Data Index: 71243 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.7583. Min Act: -0.0000

Data Index: 673150 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.5213. Min Act: -0.0000

Data Index: 260761 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.6128. Min Act: -0.0000

Data Index: 774984 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.8241. Min Act: -0.0000

Data Index: 512138 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.3507. Min Act: -0.0000

Data Index: 681310 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.5417. Min Act: -0.0000

Data Index: 651576 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 4.3884. Min Range: -4.3884

Max Act: 2.5130. Min Act: -0.0000

Data Index: 806616 (C4 (Web Text))

Max Activating Token Index: 673