Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 375 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4446. Min Act: -0.0001

Data Index: 687511 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4408. Min Act: -0.0001

Data Index: 1201931 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4179. Min Act: -0.0001

Data Index: 414632 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4147. Min Act: -0.0001

Data Index: 195697 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4183. Min Act: -0.0001

Data Index: 638030 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.4207. Min Act: -0.0001

Data Index: 820482 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3995. Min Act: -0.0001

Data Index: 1033750 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3982. Min Act: -0.0001

Data Index: 918693 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3962. Min Act: -0.0001

Data Index: 1133933 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3628. Min Act: -0.0001

Data Index: 70952 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3787. Min Act: -0.0001

Data Index: 541855 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3707. Min Act: -0.0001

Data Index: 949282 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3711. Min Act: -0.0001

Data Index: 483321 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3700. Min Act: -0.0001

Data Index: 8951 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3710. Min Act: -0.0000

Data Index: 152050 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3704. Min Act: -0.0001

Data Index: 1117208 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3547. Min Act: -0.0001

Data Index: 54608 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3795. Min Act: -0.0001

Data Index: 1274843 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3635. Min Act: -0.0001

Data Index: 1332041 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.4446. Min Range: -0.4446

Max Act: 0.3599. Min Act: -0.0001

Data Index: 154159 (C4 (Web Text))

Max Activating Token Index: 870