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

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

Neuron 1972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.3631. Min Act: -0.0000

Data Index: 1041365 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.4438. Min Act: -0.0000

Data Index: 252447 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.5253. Min Act: -0.0000

Data Index: 1116931 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.4747. Min Act: -0.0000

Data Index: 589118 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.2755. Min Act: -0.0000

Data Index: 443839 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.3439. Min Act: -0.0000

Data Index: 509809 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.3245. Min Act: -0.0000

Data Index: 1652384 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.4443. Min Act: -0.0001

Data Index: 1244097 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.1604. Min Act: -0.0000

Data Index: 356129 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.2813. Min Act: -0.0000

Data Index: 1006652 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.1323. Min Act: -0.0000

Data Index: 507538 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.1797. Min Act: -0.0000

Data Index: 743104 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.1988. Min Act: -0.0001

Data Index: 541825 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.2875. Min Act: -0.0000

Data Index: 993869 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.2746. Min Act: -0.0000

Data Index: 1110127 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 2.5253. Min Range: -2.5253

Max Act: 1.9207. Min Act: -0.0000

Data Index: 951958 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.0941. Min Act: -0.0000

Data Index: 438077 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.1001. Min Act: -0.0000

Data Index: 824173 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 2.5253. Min Range: -2.5253

Max Act: 1.9787. Min Act: -0.0000

Data Index: 16610 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 2.5253. Min Range: -2.5253

Max Act: 2.1005. Min Act: -0.0000

Data Index: 941040 (C4 (Web Text))

Max Activating Token Index: 871