Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 361 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0005

Data Index: 675850 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1199. Min Act: -0.0005

Data Index: 492597 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1092. Min Act: -0.0005

Data Index: 844188 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1228. Min Act: -0.0005

Data Index: 1220446 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1113. Min Act: -0.0005

Data Index: 669524 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0945. Min Act: -0.0005

Data Index: 772970 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1011. Min Act: -0.0005

Data Index: 959496 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1012. Min Act: -0.0005

Data Index: 1335540 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0996. Min Act: -0.0005

Data Index: 1306685 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0955. Min Act: -0.0005

Data Index: 911428 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0996. Min Act: -0.0005

Data Index: 999725 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0994. Min Act: -0.0005

Data Index: 827570 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0956. Min Act: -0.0005

Data Index: 716594 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1022. Min Act: -0.0005

Data Index: 493854 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0900. Min Act: -0.0005

Data Index: 285358 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0948. Min Act: -0.0005

Data Index: 884738 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0962. Min Act: -0.0005

Data Index: 1058844 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0955. Min Act: -0.0005

Data Index: 1043500 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0994. Min Act: -0.0005

Data Index: 860790 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0893. Min Act: -0.0005

Data Index: 140055 (C4 (Web Text))

Max Activating Token Index: 902