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

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

Neuron 3077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3193. Min Range: -4.3193

Max Act: 4.3193. Min Act: -0.0000

Data Index: 157320 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 4.3193. Min Range: -4.3193

Max Act: 4.1112. Min Act: -0.0000

Data Index: 802187 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 4.3193. Min Range: -4.3193

Max Act: 4.0765. Min Act: -0.0000

Data Index: 1291678 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.6346. Min Act: -0.0000

Data Index: 161395 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.4464. Min Act: -0.0000

Data Index: 16542 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.5946. Min Act: -0.0000

Data Index: 334651 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.3589. Min Act: -0.0000

Data Index: 732056 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.4505. Min Act: -0.0000

Data Index: 1050660 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.2777. Min Act: -0.0000

Data Index: 823098 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.3941. Min Act: -0.0000

Data Index: 495481 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.3682. Min Act: -0.0000

Data Index: 13897 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.3518. Min Act: -0.0000

Data Index: 634332 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.3026. Min Act: -0.0000

Data Index: 896923 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.4965. Min Act: -0.0000

Data Index: 314316 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.1342. Min Act: -0.0000

Data Index: 778993 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.2741. Min Act: -0.0000

Data Index: 40479 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.2311. Min Act: -0.0000

Data Index: 518232 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.0772. Min Act: -0.0000

Data Index: 1341444 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.2273. Min Act: -0.0000

Data Index: 569807 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 4.3193. Min Range: -4.3193

Max Act: 3.2141. Min Act: -0.0000

Data Index: 826501 (C4 (Web Text))

Max Activating Token Index: 182