Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1774 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.6157. Min Act: -0.0001

Data Index: 779179 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4994. Min Act: -0.0001

Data Index: 395862 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4667. Min Act: -0.0001

Data Index: 1210927 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4576. Min Act: -0.0001

Data Index: 572359 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3921. Min Act: -0.0001

Data Index: 325580 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3968. Min Act: -0.0001

Data Index: 728177 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3855. Min Act: -0.0001

Data Index: 1047369 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3757. Min Act: -0.0001

Data Index: 53502 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3803. Min Act: -0.0001

Data Index: 308801 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3821. Min Act: -0.0001

Data Index: 951475 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3693. Min Act: -0.0001

Data Index: 148805 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3531. Min Act: -0.0001

Data Index: 1352490 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3662. Min Act: -0.0001

Data Index: 367118 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3644. Min Act: -0.0001

Data Index: 1101270 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3643. Min Act: -0.0001

Data Index: 949994 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3529. Min Act: -0.0001

Data Index: 1113564 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3496. Min Act: -0.0001

Data Index: 805629 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3476. Min Act: -0.0001

Data Index: 745881 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3241. Min Act: -0.0001

Data Index: 562825 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.3408. Min Act: -0.0001

Data Index: 517513 (C4 (Web Text))

Max Activating Token Index: 961