Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 548 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2942. Min Act: -0.0005

Data Index: 737758 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2983. Min Act: -0.0005

Data Index: 127733 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2787. Min Act: -0.0005

Data Index: 1478197 (Python Code)

Max Activating Token Index: 334

Text #3

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2794. Min Act: -0.0005

Data Index: 920589 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2883. Min Act: -0.0005

Data Index: 1159574 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2579. Min Act: -0.0005

Data Index: 596726 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2665. Min Act: -0.0005

Data Index: 119430 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2711. Min Act: -0.0005

Data Index: 304962 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2616. Min Act: -0.0005

Data Index: 76615 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2422. Min Act: -0.0005

Data Index: 1040068 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2487. Min Act: -0.0005

Data Index: 1326653 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2766. Min Act: -0.0005

Data Index: 1163496 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2665. Min Act: -0.0005

Data Index: 257551 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2655. Min Act: -0.0005

Data Index: 1083080 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2474. Min Act: -0.0005

Data Index: 1317061 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2620. Min Act: -0.0005

Data Index: 609027 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2877. Min Act: -0.0005

Data Index: 947570 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2497. Min Act: -0.0005

Data Index: 1295540 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2879. Min Act: -0.0005

Data Index: 368594 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.2983. Min Range: -0.2983

Max Act: 0.2445. Min Act: -0.0005

Data Index: 205901 (C4 (Web Text))

Max Activating Token Index: 675