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

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

Neuron 1004 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: 0.8520. Min Range: -0.8520

Max Act: 0.8391. Min Act: -0.0001

Data Index: 1327286 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.8520. Min Act: -0.0001

Data Index: 365811 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7738. Min Act: -0.0001

Data Index: 584658 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7880. Min Act: -0.0001

Data Index: 812858 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7524. Min Act: -0.0000

Data Index: 168118 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7569. Min Act: -0.0001

Data Index: 377430 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7657. Min Act: -0.0000

Data Index: 754513 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7360. Min Act: -0.0000

Data Index: 440629 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7227. Min Act: -0.0001

Data Index: 365494 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6538. Min Act: -0.0001

Data Index: 1112706 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7418. Min Act: -0.0000

Data Index: 263006 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7401. Min Act: -0.0001

Data Index: 618368 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6922. Min Act: -0.0001

Data Index: 283542 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7145. Min Act: -0.0001

Data Index: 336350 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7364. Min Act: -0.0001

Data Index: 180512 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7517. Min Act: -0.0001

Data Index: 1309510 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7167. Min Act: -0.0001

Data Index: 946930 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.7210. Min Act: -0.0001

Data Index: 1125904 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6699. Min Act: -0.0001

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.8520. Min Range: -0.8520

Max Act: 0.6724. Min Act: -0.0000

Data Index: 903036 (C4 (Web Text))

Max Activating Token Index: 851