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

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

Neuron 2265 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.8975. Min Act: -0.0002

Data Index: 250524 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.6351. Min Act: -0.0002

Data Index: 199308 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.5559. Min Act: -0.0002

Data Index: 255806 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.5353. Min Act: -0.0002

Data Index: 609128 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.5906. Min Act: -0.0002

Data Index: 1264381 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.5024. Min Act: -0.0002

Data Index: 550837 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.3457. Min Act: -0.0003

Data Index: 300625 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.3099. Min Act: -0.0002

Data Index: 560652 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.3315. Min Act: -0.0002

Data Index: 619422 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.3220. Min Act: -0.0002

Data Index: 476462 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.2440. Min Act: -0.0003

Data Index: 442805 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.2533. Min Act: -0.0002

Data Index: 1183901 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.2060. Min Act: -0.0003

Data Index: 569313 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.1149. Min Act: -0.0002

Data Index: 213450 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.1732. Min Act: -0.0002

Data Index: 1344918 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.1818. Min Act: -0.0002

Data Index: 50938 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.2148. Min Act: -0.0002

Data Index: 557359 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.1544. Min Act: -0.0002

Data Index: 676683 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.1445. Min Act: -0.0002

Data Index: 26640 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 2.8975. Min Range: -2.8975

Max Act: 2.1201. Min Act: -0.0002

Data Index: 592369 (C4 (Web Text))

Max Activating Token Index: 256