Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3610. Min Act: -0.0001

Data Index: 369530 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1335503 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3495. Min Act: -0.0001

Data Index: 1343593 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3041. Min Act: -0.0001

Data Index: 159449 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2904. Min Act: -0.0001

Data Index: 47077 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2847. Min Act: -0.0001

Data Index: 767532 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3098. Min Act: -0.0001

Data Index: 359963 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.3001. Min Act: -0.0001

Data Index: 439460 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2747. Min Act: -0.0001

Data Index: 439048 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2858. Min Act: -0.0001

Data Index: 810548 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2913. Min Act: -0.0001

Data Index: 419798 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2782. Min Act: -0.0001

Data Index: 304715 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2881. Min Act: -0.0001

Data Index: 989229 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2646. Min Act: -0.0001

Data Index: 808239 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2804. Min Act: -0.0001

Data Index: 810001 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1244719 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2602. Min Act: -0.0001

Data Index: 246379 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2624. Min Act: -0.0001

Data Index: 1352763 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2596. Min Act: -0.0001

Data Index: 147563 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.3610. Min Range: -0.3610

Max Act: 0.2590. Min Act: -0.0001

Data Index: 465842 (C4 (Web Text))

Max Activating Token Index: 333