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

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

Neuron 1750 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: 0.3988. Min Range: -0.3988

Max Act: 0.3988. Min Act: -0.0001

Data Index: 912656 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3726. Min Act: -0.0001

Data Index: 519369 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3741. Min Act: -0.0001

Data Index: 482928 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3520. Min Act: -0.0001

Data Index: 1320150 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3480. Min Act: -0.0001

Data Index: 814082 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3691. Min Act: -0.0001

Data Index: 942320 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3444. Min Act: -0.0000

Data Index: 299945 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3626. Min Act: -0.0001

Data Index: 1101077 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3478. Min Act: -0.0001

Data Index: 997709 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3400. Min Act: -0.0000

Data Index: 608516 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3286. Min Act: -0.0001

Data Index: 1056014 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3162. Min Act: -0.0001

Data Index: 92827 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1239520 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3250. Min Act: -0.0001

Data Index: 296864 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1300715 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3226. Min Act: -0.0001

Data Index: 850058 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1032799 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3419. Min Act: -0.0001

Data Index: 1020638 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3280. Min Act: -0.0001

Data Index: 173862 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.3988. Min Range: -0.3988

Max Act: 0.3281. Min Act: -0.0001

Data Index: 933282 (C4 (Web Text))

Max Activating Token Index: 785