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

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

Neuron 4282 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: 0.8947. Min Range: -0.8947

Max Act: 0.8947. Min Act: -0.0000

Data Index: 903175 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1008474 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.7417. Min Act: -0.0000

Data Index: 32261 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1090838 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.5171. Min Act: -0.0000

Data Index: 519273 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1221047 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4278. Min Act: -0.0000

Data Index: 1087226 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1166677 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4855. Min Act: -0.0000

Data Index: 166909 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1272114 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1535116 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1570782 (Python Code)

Max Activating Token Index: 882

Text #12

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4639. Min Act: -0.0000

Data Index: 440819 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4468. Min Act: -0.0000

Data Index: 978544 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4643. Min Act: -0.0000

Data Index: 331561 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1573248 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4458. Min Act: -0.0000

Data Index: 436126 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4590. Min Act: -0.0000

Data Index: 759888 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4529. Min Act: -0.0000

Data Index: 269219 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.8947. Min Range: -0.8947

Max Act: 0.4420. Min Act: -0.0000

Data Index: 12532 (C4 (Web Text))

Max Activating Token Index: 85