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

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

Neuron 2125 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2893. Min Act: -0.0001

Data Index: 516245 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2906. Min Act: -0.0001

Data Index: 1105120 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2975. Min Act: -0.0001

Data Index: 913315 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2966. Min Act: -0.0001

Data Index: 424319 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2956. Min Act: -0.0001

Data Index: 397801 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2796. Min Act: -0.0001

Data Index: 446548 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2677. Min Act: -0.0001

Data Index: 790828 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2759. Min Act: -0.0001

Data Index: 746649 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2743. Min Act: -0.0001

Data Index: 1261857 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2663. Min Act: -0.0001

Data Index: 470095 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1227631 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2558. Min Act: -0.0001

Data Index: 48547 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2555. Min Act: -0.0001

Data Index: 501491 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1271763 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2428. Min Act: -0.0001

Data Index: 884089 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2653. Min Act: -0.0001

Data Index: 499084 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2422. Min Act: -0.0001

Data Index: 589313 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1092633 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2552. Min Act: -0.0001

Data Index: 376874 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.2975. Min Range: -0.2975

Max Act: 0.2413. Min Act: -0.0001

Data Index: 396691 (C4 (Web Text))

Max Activating Token Index: 942