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

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

Neuron 417 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: 1.7987. Min Range: -1.7987

Max Act: 1.7987. Min Act: -0.0000

Data Index: 1165614 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1196742 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.2910. Min Act: -0.0000

Data Index: 744256 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1101866 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.2190. Min Act: -0.0000

Data Index: 1048427 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.1448. Min Act: -0.0000

Data Index: 384271 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.2146. Min Act: -0.0000

Data Index: 691514 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.2062. Min Act: -0.0000

Data Index: 671858 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.2107. Min Act: -0.0000

Data Index: 309513 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.3457. Min Act: -0.0000

Data Index: 696448 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.1584. Min Act: -0.0000

Data Index: 565540 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.2337. Min Act: -0.0000

Data Index: 797389 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.0824. Min Act: -0.0000

Data Index: 529140 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.2061. Min Act: -0.0000

Data Index: 974618 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.1885. Min Act: -0.0000

Data Index: 931199 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.1131. Min Act: -0.0000

Data Index: 300927 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.1130. Min Act: -0.0000

Data Index: 681532 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 1.7987. Min Range: -1.7987

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1071110 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.0092. Min Act: -0.0000

Data Index: 307616 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.7987. Min Range: -1.7987

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1198502 (C4 (Web Text))

Max Activating Token Index: 740