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

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

Neuron 3109 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2445. Min Range: -1.2445

Max Act: 1.2445. Min Act: -0.0000

Data Index: 189906 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 1.2445. Min Range: -1.2445

Max Act: 1.0145. Min Act: -0.0000

Data Index: 614438 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.9739. Min Act: -0.0000

Data Index: 851246 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8867. Min Act: -0.0000

Data Index: 729979 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8766. Min Act: -0.0000

Data Index: 746766 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8500. Min Act: -0.0000

Data Index: 459246 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8670. Min Act: -0.0000

Data Index: 875395 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1301625 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8058. Min Act: -0.0000

Data Index: 350280 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8235. Min Act: -0.0000

Data Index: 629315 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8146. Min Act: -0.0000

Data Index: 104091 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.7879. Min Act: -0.0000

Data Index: 232294 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1345824 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.7765. Min Act: -0.0001

Data Index: 32080 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1318064 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8153. Min Act: -0.0000

Data Index: 450551 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.7961. Min Act: -0.0000

Data Index: 27961 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1304215 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1100650 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 1.2445. Min Range: -1.2445

Max Act: 0.8155. Min Act: -0.0000

Data Index: 796638 (C4 (Web Text))

Max Activating Token Index: 182