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

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

Neuron 3654 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2068. Min Act: -0.0001

Data Index: 864862 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.4776. Min Act: -0.0000

Data Index: 609698 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2988. Min Act: -0.0001

Data Index: 34844 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.3735. Min Act: -0.0001

Data Index: 326438 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.4275. Min Act: -0.0000

Data Index: 459040 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2623. Min Act: -0.0001

Data Index: 308447 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2262. Min Act: -0.0000

Data Index: 978083 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2553. Min Act: -0.0001

Data Index: 719941 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1665. Min Act: -0.0001

Data Index: 918532 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1585. Min Act: -0.0001

Data Index: 920138 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2755. Min Act: -0.0000

Data Index: 1196138 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0856. Min Act: -0.0001

Data Index: 73142 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.2740. Min Act: -0.0000

Data Index: 211260 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0666. Min Act: -0.0001

Data Index: 1083583 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1357. Min Act: -0.0001

Data Index: 610857 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0859. Min Act: -0.0001

Data Index: 161064 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1298. Min Act: -0.0000

Data Index: 222453 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1400. Min Act: -0.0000

Data Index: 548096 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.1005. Min Act: -0.0001

Data Index: 838086 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 1.4776. Min Range: -1.4776

Max Act: 1.0637. Min Act: -0.0001

Data Index: 11478 (C4 (Web Text))

Max Activating Token Index: 841