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

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

Neuron 2178 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.4053. Min Act: -0.0001

Data Index: 584627 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3835. Min Act: -0.0001

Data Index: 510607 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3755. Min Act: -0.0001

Data Index: 421475 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3686. Min Act: -0.0001

Data Index: 102147 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3539. Min Act: -0.0001

Data Index: 641284 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3630. Min Act: -0.0001

Data Index: 185889 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3638. Min Act: -0.0001

Data Index: 246916 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3455. Min Act: -0.0001

Data Index: 1315931 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3522. Min Act: -0.0001

Data Index: 1099854 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3479. Min Act: -0.0001

Data Index: 1162644 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3126. Min Act: -0.0001

Data Index: 343817 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3579. Min Act: -0.0001

Data Index: 28957 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3329. Min Act: -0.0001

Data Index: 936703 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3477. Min Act: -0.0001

Data Index: 293262 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3511. Min Act: -0.0001

Data Index: 430591 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3337. Min Act: -0.0001

Data Index: 588035 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3333. Min Act: -0.0001

Data Index: 1292830 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3218. Min Act: -0.0001

Data Index: 1303240 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3219. Min Act: -0.0001

Data Index: 296006 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3325. Min Act: -0.0001

Data Index: 700764 (C4 (Web Text))

Max Activating Token Index: 749