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

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

Neuron 168 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: 0.3167. Min Range: -0.3167

Max Act: 0.3167. Min Act: -0.0001

Data Index: 877295 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2686. Min Act: -0.0001

Data Index: 952512 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2801. Min Act: -0.0001

Data Index: 720224 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2973. Min Act: -0.0001

Data Index: 638700 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1295061 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2843. Min Act: -0.0001

Data Index: 1000945 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2804. Min Act: -0.0001

Data Index: 380078 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2658. Min Act: -0.0001

Data Index: 746582 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2580. Min Act: -0.0001

Data Index: 424220 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2661. Min Act: -0.0001

Data Index: 462477 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2667. Min Act: -0.0001

Data Index: 264271 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2752. Min Act: -0.0001

Data Index: 366750 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2612. Min Act: -0.0001

Data Index: 240873 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2539. Min Act: -0.0001

Data Index: 963440 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2822. Min Act: -0.0001

Data Index: 415946 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2699. Min Act: -0.0001

Data Index: 1306391 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2595. Min Act: -0.0001

Data Index: 343141 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2573. Min Act: -0.0001

Data Index: 530600 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2559. Min Act: -0.0001

Data Index: 804824 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2664. Min Act: -0.0001

Data Index: 1162183 (C4 (Web Text))

Max Activating Token Index: 669