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

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

Neuron 2539 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3290. Min Act: -0.0001

Data Index: 606926 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3477. Min Act: -0.0001

Data Index: 1107317 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3303. Min Act: -0.0001

Data Index: 810944 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3176. Min Act: -0.0001

Data Index: 570146 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3144. Min Act: -0.0001

Data Index: 589159 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3347. Min Act: -0.0001

Data Index: 1279726 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3384. Min Act: -0.0001

Data Index: 1207207 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.3137. Min Act: -0.0001

Data Index: 236257 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2689. Min Act: -0.0001

Data Index: 225596 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2908. Min Act: -0.0001

Data Index: 558999 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2801. Min Act: -0.0001

Data Index: 542263 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2891. Min Act: -0.0001

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2912. Min Act: -0.0001

Data Index: 551895 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2750. Min Act: -0.0001

Data Index: 294945 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1033960 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2718. Min Act: -0.0001

Data Index: 615422 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2538. Min Act: -0.0001

Data Index: 776851 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2633. Min Act: -0.0001

Data Index: 863218 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2631. Min Act: -0.0001

Data Index: 724985 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.3477. Min Range: -0.3477

Max Act: 0.2436. Min Act: -0.0001

Data Index: 42858 (C4 (Web Text))

Max Activating Token Index: 216