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

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

Neuron 3554 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7479. Min Act: -0.0000

Data Index: 853237 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1118597 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6976. Min Act: -0.0000

Data Index: 562873 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7388. Min Act: -0.0001

Data Index: 372716 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.7160. Min Act: -0.0000

Data Index: 832110 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1226580 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1253926 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6595. Min Act: -0.0000

Data Index: 321532 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6605. Min Act: -0.0000

Data Index: 38465 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6581. Min Act: -0.0001

Data Index: 1046368 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6294. Min Act: -0.0001

Data Index: 404837 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6450. Min Act: -0.0000

Data Index: 121687 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6443. Min Act: -0.0001

Data Index: 1293781 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1306886 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6135. Min Act: -0.0000

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6148. Min Act: -0.0000

Data Index: 530080 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.5864. Min Act: -0.0001

Data Index: 1067274 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.5892. Min Act: -0.0000

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.6264. Min Act: -0.0001

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.7479. Min Range: -0.7479

Max Act: 0.5980. Min Act: -0.0001

Data Index: 264807 (C4 (Web Text))

Max Activating Token Index: 52