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

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

Neuron 130 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.3118. Min Act: -0.0001

Data Index: 676111 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2782. Min Act: -0.0001

Data Index: 925699 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1001122 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2787. Min Act: -0.0001

Data Index: 463603 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2864. Min Act: -0.0001

Data Index: 572928 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2511. Min Act: -0.0001

Data Index: 157280 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2684. Min Act: -0.0001

Data Index: 1027450 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2545. Min Act: -0.0001

Data Index: 871943 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2648. Min Act: -0.0001

Data Index: 878824 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2737. Min Act: -0.0001

Data Index: 957506 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2638. Min Act: -0.0001

Data Index: 201187 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2613. Min Act: -0.0001

Data Index: 773414 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2600. Min Act: -0.0001

Data Index: 460343 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2685. Min Act: -0.0001

Data Index: 353339 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2668. Min Act: -0.0001

Data Index: 1246835 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1231998 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2643. Min Act: -0.0001

Data Index: 1265463 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2528. Min Act: -0.0001

Data Index: 41689 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2523. Min Act: -0.0001

Data Index: 508513 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.3118. Min Range: -0.3118

Max Act: 0.2411. Min Act: -0.0001

Data Index: 856720 (C4 (Web Text))

Max Activating Token Index: 628