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

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

Neuron 1025 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.4089. Min Act: -0.0001

Data Index: 20316 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3811. Min Act: -0.0000

Data Index: 984958 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3652. Min Act: -0.0001

Data Index: 1503601 (Python Code)

Max Activating Token Index: 429

Text #3

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3328. Min Act: -0.0001

Data Index: 1113405 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2973. Min Act: -0.0001

Data Index: 445622 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1460570 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3300. Min Act: -0.0001

Data Index: 43871 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3089. Min Act: -0.0001

Data Index: 136951 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3293. Min Act: -0.0001

Data Index: 327592 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3277. Min Act: -0.0001

Data Index: 1060639 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3236. Min Act: -0.0000

Data Index: 920188 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3227. Min Act: -0.0001

Data Index: 1654296 (Python Code)

Max Activating Token Index: 667

Text #12

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3032. Min Act: -0.0001

Data Index: 1533978 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1392328 (Python Code)

Max Activating Token Index: 869

Text #14

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3451. Min Act: -0.0000

Data Index: 428756 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1183944 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.2858. Min Act: -0.0001

Data Index: 672395 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1626913 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3151. Min Act: -0.0001

Data Index: 1355500 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.4089. Min Range: -0.4089

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1365899 (Python Code)

Max Activating Token Index: 698