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

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

Neuron 546 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6956. Min Act: -0.0001

Data Index: 14322 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6445. Min Act: -0.0001

Data Index: 562427 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6527. Min Act: -0.0000

Data Index: 386381 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6655. Min Act: -0.0001

Data Index: 15284 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6371. Min Act: -0.0001

Data Index: 159395 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6275. Min Act: -0.0001

Data Index: 234204 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6394. Min Act: -0.0001

Data Index: 1201789 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1120130 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6112. Min Act: -0.0000

Data Index: 140185 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5842. Min Act: -0.0000

Data Index: 249726 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5822. Min Act: -0.0000

Data Index: 648399 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.6008. Min Act: -0.0000

Data Index: 154004 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5668. Min Act: -0.0001

Data Index: 883745 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.4841. Min Act: -0.0001

Data Index: 1197582 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5443. Min Act: -0.0001

Data Index: 622878 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5223. Min Act: -0.0000

Data Index: 113167 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5209. Min Act: -0.0000

Data Index: 379728 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5005. Min Act: -0.0000

Data Index: 888617 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1073988 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.6956. Min Range: -0.6956

Max Act: 0.5466. Min Act: -0.0000

Data Index: 736343 (C4 (Web Text))

Max Activating Token Index: 769