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

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

Neuron 3796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0348. Min Range: -1.0348

Max Act: 1.0348. Min Act: -0.0001

Data Index: 36040 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.9183. Min Act: -0.0001

Data Index: 1336821 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8588. Min Act: -0.0001

Data Index: 523861 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.9308. Min Act: -0.0001

Data Index: 1203433 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8690. Min Act: -0.0001

Data Index: 164467 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8479. Min Act: -0.0001

Data Index: 573626 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1250307 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8842. Min Act: -0.0001

Data Index: 558011 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8498. Min Act: -0.0001

Data Index: 361617 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8387. Min Act: -0.0001

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7965. Min Act: -0.0001

Data Index: 1215074 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7905. Min Act: -0.0001

Data Index: 1173621 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.8048. Min Act: -0.0001

Data Index: 1246592 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7817. Min Act: -0.0001

Data Index: 1323723 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7548. Min Act: -0.0001

Data Index: 452778 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7931. Min Act: -0.0001

Data Index: 918560 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7293. Min Act: -0.0001

Data Index: 166703 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7682. Min Act: -0.0001

Data Index: 108784 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7474. Min Act: -0.0001

Data Index: 1128472 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.0348. Min Range: -1.0348

Max Act: 0.7976. Min Act: -0.0001

Data Index: 1264433 (C4 (Web Text))

Max Activating Token Index: 791