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

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

Neuron 1892 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3542. Min Range: -4.3542

Max Act: 4.2634. Min Act: -0.0000

Data Index: 938084 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 4.3542. Min Range: -4.3542

Max Act: 4.3542. Min Act: -0.0000

Data Index: 75437 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 4.3542. Min Range: -4.3542

Max Act: 4.1471. Min Act: -0.0000

Data Index: 1035675 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.5491. Min Act: -0.0000

Data Index: 1334600 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 4.3542. Min Range: -4.3542

Max Act: 4.0496. Min Act: -0.0000

Data Index: 146274 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.5591. Min Act: -0.0000

Data Index: 444062 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.6239. Min Act: -0.0000

Data Index: 786208 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.3532. Min Act: -0.0000

Data Index: 448262 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.1297. Min Act: -0.0000

Data Index: 1266494 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.1286. Min Act: -0.0000

Data Index: 810590 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.0176. Min Act: -0.0000

Data Index: 656206 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.0644. Min Act: -0.0000

Data Index: 116011 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 4.3542. Min Range: -4.3542

Max Act: 2.7864. Min Act: -0.0000

Data Index: 30193 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 4.3542. Min Range: -4.3542

Max Act: 2.7602. Min Act: -0.0000

Data Index: 127464 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 4.3542. Min Range: -4.3542

Max Act: 3.0409. Min Act: -0.0000

Data Index: 337690 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 4.3542. Min Range: -4.3542

Max Act: 2.8638. Min Act: -0.0000

Data Index: 1318092 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 4.3542. Min Range: -4.3542

Max Act: 2.7081. Min Act: -0.0000

Data Index: 1339590 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 4.3542. Min Range: -4.3542

Max Act: 2.6626. Min Act: -0.0000

Data Index: 138645 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 4.3542. Min Range: -4.3542

Max Act: 2.4913. Min Act: -0.0000

Data Index: 400302 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 4.3542. Min Range: -4.3542

Max Act: 2.7117. Min Act: -0.0000

Data Index: 1144402 (C4 (Web Text))

Max Activating Token Index: 997