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

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

Neuron 4492 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0275. Min Range: -3.0275

Max Act: 3.0275. Min Act: -0.0000

Data Index: 444426 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.9344. Min Act: -0.0000

Data Index: 957360 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.7004. Min Act: -0.0000

Data Index: 75039 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.5433. Min Act: -0.0000

Data Index: 1126092 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.4305. Min Act: -0.0000

Data Index: 883403 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.3909. Min Act: -0.0000

Data Index: 125761 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.3296. Min Act: -0.0000

Data Index: 382521 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.2531. Min Act: -0.0000

Data Index: 982435 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.0393. Min Act: -0.0000

Data Index: 441071 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.2435. Min Act: -0.0000

Data Index: 30360 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.1170. Min Act: -0.0000

Data Index: 923128 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.1861. Min Act: -0.0000

Data Index: 570276 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.1507. Min Act: -0.0000

Data Index: 996472 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.1366. Min Act: -0.0000

Data Index: 2035 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 3.0275. Min Range: -3.0275

Max Act: 1.9299. Min Act: -0.0000

Data Index: 800645 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.0047. Min Act: -0.0000

Data Index: 1211210 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.0496. Min Act: -0.0001

Data Index: 1202466 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.0567. Min Act: -0.0000

Data Index: 452445 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.0648. Min Act: -0.0001

Data Index: 3478 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 3.0275. Min Range: -3.0275

Max Act: 2.0463. Min Act: -0.0000

Data Index: 66444 (C4 (Web Text))

Max Activating Token Index: 331