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

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

Neuron 3763 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1183526 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1137330 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2997. Min Act: -0.0000

Data Index: 117528 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2927. Min Act: -0.0000

Data Index: 261297 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2771. Min Act: -0.0000

Data Index: 805119 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2944. Min Act: -0.0000

Data Index: 529685 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1261867 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2817. Min Act: -0.0000

Data Index: 525555 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1357751 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2758. Min Act: -0.0000

Data Index: 948099 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2786. Min Act: -0.0001

Data Index: 1127434 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2746. Min Act: -0.0000

Data Index: 854377 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2624. Min Act: -0.0000

Data Index: 244106 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1237530 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2511. Min Act: -0.0000

Data Index: 871989 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1285014 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2594. Min Act: -0.0001

Data Index: 526867 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2602. Min Act: -0.0001

Data Index: 453492 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1182758 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2591. Min Act: -0.0000

Data Index: 966504 (C4 (Web Text))

Max Activating Token Index: 307