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

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

Neuron 2082 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: 0.6303. Min Range: -0.6303

Max Act: 0.6303. Min Act: -0.0001

Data Index: 1191255 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5903. Min Act: -0.0001

Data Index: 728486 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5493. Min Act: -0.0001

Data Index: 822306 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.5209. Min Act: -0.0001

Data Index: 825797 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4846. Min Act: -0.0001

Data Index: 129701 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4978. Min Act: -0.0001

Data Index: 537843 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4722. Min Act: -0.0001

Data Index: 912574 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4549. Min Act: -0.0001

Data Index: 289977 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4699. Min Act: -0.0001

Data Index: 644835 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4666. Min Act: -0.0001

Data Index: 342897 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4489. Min Act: 0.0000

Data Index: 386296 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4371. Min Act: -0.0001

Data Index: 958928 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4486. Min Act: -0.0001

Data Index: 616896 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4468. Min Act: -0.0001

Data Index: 189920 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1063317 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4471. Min Act: -0.0001

Data Index: 987639 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4406. Min Act: -0.0001

Data Index: 803319 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4236. Min Act: -0.0001

Data Index: 706117 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4369. Min Act: -0.0001

Data Index: 1324739 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.6303. Min Range: -0.6303

Max Act: 0.4380. Min Act: -0.0001

Data Index: 993656 (C4 (Web Text))

Max Activating Token Index: 933