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

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

Neuron 803 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3416. Min Act: -0.0001

Data Index: 325593 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0001

Data Index: 600659 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3192. Min Act: -0.0001

Data Index: 1102906 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3282. Min Act: -0.0001

Data Index: 144918 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3445. Min Act: -0.0001

Data Index: 451459 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3270. Min Act: -0.0001

Data Index: 857004 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2475. Min Act: -0.0001

Data Index: 1286254 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3500. Min Act: -0.0001

Data Index: 462938 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2982. Min Act: -0.0001

Data Index: 328274 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3261. Min Act: -0.0001

Data Index: 384861 (C4 (Web Text))

Max Activating Token Index: 991

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3240. Min Act: -0.0001

Data Index: 477176 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2789. Min Act: -0.0001

Data Index: 714190 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1335104 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3090. Min Act: -0.0001

Data Index: 443361 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3033. Min Act: -0.0001

Data Index: 105996 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3046. Min Act: -0.0001

Data Index: 235448 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2600. Min Act: -0.0001

Data Index: 229337 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3133. Min Act: -0.0001

Data Index: 18662 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3280. Min Act: -0.0001

Data Index: 1307013 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2977. Min Act: -0.0001

Data Index: 417845 (C4 (Web Text))

Max Activating Token Index: 835