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

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

Neuron 2588 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: 1.8581. Min Range: -1.8581

Max Act: 1.8152. Min Act: -0.0000

Data Index: 365993 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.7100. Min Act: -0.0000

Data Index: 244741 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.8581. Min Act: -0.0000

Data Index: 488757 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.4476. Min Act: -0.0000

Data Index: 59150 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.4541. Min Act: -0.0000

Data Index: 957616 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.4696. Min Act: -0.0000

Data Index: 161499 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.4085. Min Act: -0.0000

Data Index: 819116 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.3802. Min Act: -0.0000

Data Index: 81209 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1095862 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1048014 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.3123. Min Act: -0.0000

Data Index: 1298354 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.3838. Min Act: -0.0000

Data Index: 831271 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.4350. Min Act: -0.0000

Data Index: 590988 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.2420. Min Act: -0.0000

Data Index: 850456 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.3416. Min Act: -0.0000

Data Index: 501540 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.2881. Min Act: -0.0000

Data Index: 1299465 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.3062. Min Act: -0.0000

Data Index: 265949 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.3045. Min Act: -0.0000

Data Index: 93219 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.2570. Min Act: -0.0000

Data Index: 182184 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.8581. Min Range: -1.8581

Max Act: 1.2113. Min Act: -0.0000

Data Index: 178170 (C4 (Web Text))

Max Activating Token Index: 132