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

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

Neuron 4987 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: 0.9434. Min Range: -0.9434

Max Act: 0.9434. Min Act: -0.0000

Data Index: 719972 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.9164. Min Act: -0.0000

Data Index: 41975 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.9030. Min Act: -0.0000

Data Index: 112956 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8572. Min Act: -0.0000

Data Index: 307498 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8204. Min Act: -0.0000

Data Index: 87481 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8862. Min Act: -0.0000

Data Index: 110055 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.8185. Min Act: -0.0000

Data Index: 309565 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7841. Min Act: -0.0000

Data Index: 949416 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7682. Min Act: -0.0000

Data Index: 442072 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1092811 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7832. Min Act: -0.0000

Data Index: 534689 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7654. Min Act: -0.0000

Data Index: 569741 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7482. Min Act: -0.0000

Data Index: 280246 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7591. Min Act: -0.0000

Data Index: 7978 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6690. Min Act: -0.0000

Data Index: 348937 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7354. Min Act: -0.0000

Data Index: 440477 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.6402. Min Act: -0.0000

Data Index: 715180 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1019583 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7585. Min Act: -0.0000

Data Index: 92437 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.9434. Min Range: -0.9434

Max Act: 0.7233. Min Act: -0.0000

Data Index: 671358 (C4 (Web Text))

Max Activating Token Index: 443