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

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

Neuron 2707 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: 3.4284. Min Range: -3.4284

Max Act: 3.4284. Min Act: -0.0000

Data Index: 1096817 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 3.4284. Min Range: -3.4284

Max Act: 3.0096. Min Act: -0.0000

Data Index: 522904 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.6668. Min Act: -0.0000

Data Index: 637733 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.7327. Min Act: -0.0000

Data Index: 151586 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.5377. Min Act: -0.0000

Data Index: 1546380 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.5267. Min Act: -0.0000

Data Index: 236663 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.7422. Min Act: -0.0000

Data Index: 887103 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.4579. Min Act: -0.0000

Data Index: 1414734 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.5610. Min Act: -0.0000

Data Index: 1625442 (Python Code)

Max Activating Token Index: 278

Text #9

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.3080. Min Act: -0.0000

Data Index: 1518781 (Python Code)

Max Activating Token Index: 399

Text #10

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.3070. Min Act: -0.0000

Data Index: 325272 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.2927. Min Act: -0.0000

Data Index: 1360160 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.4317. Min Act: -0.0000

Data Index: 1202334 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.2114. Min Act: -0.0000

Data Index: 1484921 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1479383 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.2967. Min Act: -0.0000

Data Index: 1477889 (Python Code)

Max Activating Token Index: 117

Text #16

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.2890. Min Act: -0.0000

Data Index: 1384483 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1415534 (Python Code)

Max Activating Token Index: 995

Text #18

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.2545. Min Act: -0.0000

Data Index: 1624618 (Python Code)

Max Activating Token Index: 683

Text #19

Max Range: 3.4284. Min Range: -3.4284

Max Act: 2.2280. Min Act: -0.0000

Data Index: 1566140 (Python Code)

Max Activating Token Index: 504