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

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

Neuron 3991 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: 1.9489. Min Range: -1.9489

Max Act: 1.9489. Min Act: -0.0000

Data Index: 1102849 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6747. Min Act: -0.0000

Data Index: 716205 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.5582. Min Act: -0.0000

Data Index: 1342168 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.6148. Min Act: -0.0000

Data Index: 874255 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1387125 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.4739. Min Act: -0.0000

Data Index: 1344518 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.4787. Min Act: -0.0000

Data Index: 613315 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.2927. Min Act: -0.0000

Data Index: 503131 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1432342 (Python Code)

Max Activating Token Index: 215

Text #9

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1154959 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.4232. Min Act: -0.0000

Data Index: 1318499 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1206356 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3533. Min Act: -0.0000

Data Index: 691280 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3361. Min Act: -0.0000

Data Index: 1656641 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.4745. Min Act: -0.0000

Data Index: 831450 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1507827 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1326092 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1499809 (Python Code)

Max Activating Token Index: 320

Text #18

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3232. Min Act: -0.0000

Data Index: 54643 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.9489. Min Range: -1.9489

Max Act: 1.3484. Min Act: -0.0000

Data Index: 1392983 (Python Code)

Max Activating Token Index: 644