Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1194 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3934. Min Range: -2.3934

Max Act: 2.3934. Min Act: -0.0000

Data Index: 542648 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 2.3934. Min Range: -2.3934

Max Act: 2.3569. Min Act: -0.0000

Data Index: 842882 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 2.3934. Min Range: -2.3934

Max Act: 2.3073. Min Act: -0.0000

Data Index: 377331 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 2.3934. Min Range: -2.3934

Max Act: 2.2683. Min Act: -0.0000

Data Index: 205393 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 2.3934. Min Range: -2.3934

Max Act: 2.0206. Min Act: -0.0000

Data Index: 194802 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 2.3934. Min Range: -2.3934

Max Act: 2.1696. Min Act: -0.0000

Data Index: 833220 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.5440. Min Act: -0.0000

Data Index: 22325 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 2.3934. Min Range: -2.3934

Max Act: 2.1089. Min Act: -0.0000

Data Index: 1035521 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.8465. Min Act: -0.0000

Data Index: 1461000 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.7086. Min Act: -0.0000

Data Index: 1491885 (Python Code)

Max Activating Token Index: 791

Text #10

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.8899. Min Act: -0.0000

Data Index: 1390928 (Python Code)

Max Activating Token Index: 638

Text #11

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.7547. Min Act: -0.0000

Data Index: 1194089 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.7062. Min Act: -0.0000

Data Index: 50181 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.7001. Min Act: -0.0000

Data Index: 930718 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.7582. Min Act: -0.0000

Data Index: 884894 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1152611 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.4144. Min Act: -0.0000

Data Index: 1379537 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.5358. Min Act: -0.0000

Data Index: 1272320 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.2131. Min Act: -0.0000

Data Index: 1235392 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 2.3934. Min Range: -2.3934

Max Act: 1.5188. Min Act: -0.0000

Data Index: 815738 (C4 (Web Text))

Max Activating Token Index: 222