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

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

Neuron 2840 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: 0.2896. Min Range: -0.2896

Max Act: 0.2896. Min Act: -0.0000

Data Index: 617053 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2653. Min Act: -0.0000

Data Index: 712501 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2856. Min Act: -0.0001

Data Index: 398593 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1351674 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2680. Min Act: -0.0000

Data Index: 344206 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1090305 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2656. Min Act: -0.0000

Data Index: 381357 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2727. Min Act: -0.0001

Data Index: 709769 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2450. Min Act: -0.0000

Data Index: 195007 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2598. Min Act: -0.0000

Data Index: 389955 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2590. Min Act: -0.0001

Data Index: 1153624 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2407. Min Act: -0.0001

Data Index: 1186998 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2573. Min Act: -0.0001

Data Index: 97018 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2381. Min Act: -0.0000

Data Index: 764260 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2426. Min Act: -0.0001

Data Index: 855209 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2342. Min Act: -0.0000

Data Index: 852973 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2575. Min Act: -0.0001

Data Index: 949311 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2375. Min Act: -0.0001

Data Index: 224458 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1133339 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2394. Min Act: -0.0000

Data Index: 429243 (C4 (Web Text))

Max Activating Token Index: 583