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

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

Neuron 1277 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2884. Min Range: -4.2884

Max Act: 4.2071. Min Act: -0.0000

Data Index: 1650724 (Python Code)

Max Activating Token Index: 933

Text #1

Max Range: 4.2884. Min Range: -4.2884

Max Act: 4.2032. Min Act: -0.0000

Data Index: 1133621 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 4.2884. Min Range: -4.2884

Max Act: 4.2884. Min Act: -0.0000

Data Index: 1592288 (Python Code)

Max Activating Token Index: 432

Text #3

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.6277. Min Act: -0.0000

Data Index: 1036083 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.6239. Min Act: -0.0000

Data Index: 1477157 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.4926. Min Act: 0.0000

Data Index: 1028272 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.4938. Min Act: -0.0000

Data Index: 693205 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.6401. Min Act: -0.0000

Data Index: 723952 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.7098. Min Act: -0.0000

Data Index: 1298395 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.3204. Min Act: -0.0000

Data Index: 1474654 (Python Code)

Max Activating Token Index: 581

Text #10

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.3267. Min Act: -0.0000

Data Index: 382136 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.4163. Min Act: -0.0000

Data Index: 446417 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.4143. Min Act: -0.0000

Data Index: 925699 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.0908. Min Act: -0.0000

Data Index: 727537 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.1921. Min Act: -0.0000

Data Index: 1626479 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 4.2884. Min Range: -4.2884

Max Act: 2.8619. Min Act: -0.0000

Data Index: 1235982 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.3194. Min Act: -0.0000

Data Index: 210651 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.2271. Min Act: -0.0000

Data Index: 447378 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 4.2884. Min Range: -4.2884

Max Act: 2.9344. Min Act: -0.0000

Data Index: 1306245 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 4.2884. Min Range: -4.2884

Max Act: 3.0891. Min Act: -0.0000

Data Index: 1652077 (Python Code)

Max Activating Token Index: 926