Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 566 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0288. Min Range: -3.0288

Max Act: 3.0288. Min Act: -0.0001

Data Index: 263416 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 3.0288. Min Range: -3.0288

Max Act: 2.9529. Min Act: -0.0001

Data Index: 1160708 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 3.0288. Min Range: -3.0288

Max Act: 2.3078. Min Act: -0.0001

Data Index: 611538 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 3.0288. Min Range: -3.0288

Max Act: 2.4765. Min Act: -0.0001

Data Index: 1213414 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.0288. Min Range: -3.0288

Max Act: 2.0702. Min Act: -0.0001

Data Index: 537253 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 3.0288. Min Range: -3.0288

Max Act: 2.1157. Min Act: -0.0001

Data Index: 645778 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.8026. Min Act: -0.0001

Data Index: 409928 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.7843. Min Act: -0.0001

Data Index: 218705 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.6152. Min Act: -0.0001

Data Index: 664379 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.6671. Min Act: -0.0001

Data Index: 1262617 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.5939. Min Act: -0.0001

Data Index: 1179047 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.5407. Min Act: -0.0001

Data Index: 641054 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.3283. Min Act: -0.0001

Data Index: 49618 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.3922. Min Act: -0.0001

Data Index: 1327680 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.4732. Min Act: -0.0000

Data Index: 637682 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.1666. Min Act: -0.0001

Data Index: 998224 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.3541. Min Act: -0.0001

Data Index: 419979 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.2817. Min Act: -0.0000

Data Index: 706904 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 3.0288. Min Range: -3.0288

Max Act: 1.2980. Min Act: -0.0001

Data Index: 544843 (C4 (Web Text))

Max Activating Token Index: 554