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

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

Neuron 242 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: 2.9705. Min Range: -2.9705

Max Act: 2.9705. Min Act: -0.0000

Data Index: 1176273 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 2.9705. Min Range: -2.9705

Max Act: 2.5320. Min Act: -0.0000

Data Index: 1289554 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 2.9705. Min Range: -2.9705

Max Act: 2.2777. Min Act: -0.0000

Data Index: 942404 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 2.9705. Min Range: -2.9705

Max Act: 2.0682. Min Act: -0.0000

Data Index: 460932 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.8469. Min Act: -0.0000

Data Index: 652391 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.4437. Min Act: -0.0000

Data Index: 1048777 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.4018. Min Act: -0.0000

Data Index: 758158 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1247464 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.4881. Min Act: -0.0000

Data Index: 814001 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.3861. Min Act: -0.0000

Data Index: 439223 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.3879. Min Act: -0.0000

Data Index: 582094 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.3029. Min Act: -0.0000

Data Index: 637392 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.2379. Min Act: -0.0000

Data Index: 279441 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.0697. Min Act: -0.0000

Data Index: 150830 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.1612. Min Act: -0.0000

Data Index: 331350 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.2130. Min Act: -0.0000

Data Index: 89192 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.1681. Min Act: -0.0000

Data Index: 607810 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.1993. Min Act: -0.0000

Data Index: 369376 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.2136. Min Act: -0.0000

Data Index: 119289 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 2.9705. Min Range: -2.9705

Max Act: 1.2065. Min Act: -0.0000

Data Index: 149613 (C4 (Web Text))

Max Activating Token Index: 46