Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4865 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1285721 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.2093. Min Act: -0.0000

Data Index: 664274 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1118384 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0591. Min Act: -0.0000

Data Index: 683211 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0543. Min Act: -0.0000

Data Index: 571880 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0789. Min Act: -0.0000

Data Index: 930626 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9203. Min Act: -0.0000

Data Index: 395561 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1191267 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9475. Min Act: -0.0000

Data Index: 594507 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9458. Min Act: -0.0000

Data Index: 246083 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9434. Min Act: -0.0000

Data Index: 342543 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9918. Min Act: -0.0000

Data Index: 209688 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1031146 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9135. Min Act: -0.0000

Data Index: 134682 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8860. Min Act: -0.0000

Data Index: 50394 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8229. Min Act: -0.0000

Data Index: 169947 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8094. Min Act: -0.0000

Data Index: 394976 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8046. Min Act: -0.0000

Data Index: 150035 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8488. Min Act: -0.0000

Data Index: 5548 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8489. Min Act: -0.0000

Data Index: 36641 (C4 (Web Text))

Max Activating Token Index: 140