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

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

Neuron 625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.4724. Min Act: -0.0000

Data Index: 696862 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3620. Min Act: -0.0000

Data Index: 149588 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3152. Min Act: -0.0001

Data Index: 2532 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3154. Min Act: -0.0000

Data Index: 570944 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3305. Min Act: -0.0001

Data Index: 679420 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3176. Min Act: -0.0000

Data Index: 778428 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2992. Min Act: -0.0001

Data Index: 980225 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.3006. Min Act: -0.0000

Data Index: 519901 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2977. Min Act: -0.0001

Data Index: 294977 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2977. Min Act: -0.0000

Data Index: 3346 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2967. Min Act: -0.0000

Data Index: 174837 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2809. Min Act: -0.0000

Data Index: 260357 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1041287 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1177180 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1119887 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2773. Min Act: -0.0001

Data Index: 314255 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2778. Min Act: -0.0000

Data Index: 283591 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2592. Min Act: -0.0001

Data Index: 96978 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2666. Min Act: -0.0001

Data Index: 789876 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.4724. Min Range: -0.4724

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1148458 (C4 (Web Text))

Max Activating Token Index: 497