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

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

Neuron 4006 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3957. Min Range: -3.3957

Max Act: 3.3957. Min Act: -0.0001

Data Index: 1108682 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.8512. Min Act: -0.0001

Data Index: 1011552 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 3.3957. Min Range: -3.3957

Max Act: 3.0593. Min Act: -0.0001

Data Index: 119634 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.7758. Min Act: -0.0001

Data Index: 134737 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.7522. Min Act: -0.0001

Data Index: 134104 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.6180. Min Act: -0.0001

Data Index: 822747 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.8354. Min Act: -0.0001

Data Index: 1171506 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.6727. Min Act: -0.0001

Data Index: 323007 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.5353. Min Act: -0.0001

Data Index: 483217 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.5098. Min Act: -0.0001

Data Index: 755668 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.6157. Min Act: -0.0001

Data Index: 947898 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.4726. Min Act: -0.0001

Data Index: 164666 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.3157. Min Act: -0.0001

Data Index: 1031475 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.4242. Min Act: -0.0001

Data Index: 718489 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.3869. Min Act: -0.0001

Data Index: 735977 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.5227. Min Act: -0.0001

Data Index: 917239 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.3844. Min Act: -0.0001

Data Index: 930286 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.2635. Min Act: -0.0001

Data Index: 88919 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.3796. Min Act: -0.0001

Data Index: 553291 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 3.3957. Min Range: -3.3957

Max Act: 2.3694. Min Act: -0.0001

Data Index: 1267390 (C4 (Web Text))

Max Activating Token Index: 772