Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3077 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4700. Min Act: -0.0002

Data Index: 806326 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4958. Min Act: -0.0002

Data Index: 424930 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4557. Min Act: -0.0001

Data Index: 423998 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4893. Min Act: -0.0001

Data Index: 806587 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4778. Min Act: -0.0001

Data Index: 1061584 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4560. Min Act: -0.0001

Data Index: 680370 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4163. Min Act: -0.0001

Data Index: 397946 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4100. Min Act: -0.0002

Data Index: 259445 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4480. Min Act: -0.0001

Data Index: 486558 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4355. Min Act: -0.0002

Data Index: 1268232 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4669. Min Act: -0.0001

Data Index: 680738 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4110. Min Act: -0.0001

Data Index: 314626 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.2864. Min Act: -0.0002

Data Index: 110439 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3392. Min Act: -0.0002

Data Index: 862803 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4650. Min Act: -0.0002

Data Index: 77588 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3240. Min Act: -0.0002

Data Index: 246052 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3605. Min Act: -0.0001

Data Index: 195579 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3964. Min Act: -0.0001

Data Index: 1271984 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.4057. Min Act: -0.0002

Data Index: 1023172 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.4958. Min Range: -0.4958

Max Act: 0.3879. Min Act: -0.0001

Data Index: 1085476 (C4 (Web Text))

Max Activating Token Index: 424