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

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

Neuron 2247 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1681. Min Act: -0.0001

Data Index: 37040 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.3147. Min Act: -0.0001

Data Index: 9448 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.3667. Min Act: -0.0001

Data Index: 348431 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.8690. Min Act: -0.0001

Data Index: 297003 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.7033. Min Act: -0.0001

Data Index: 1324332 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.9545. Min Act: -0.0001

Data Index: 109298 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.6612. Min Act: -0.0001

Data Index: 549655 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.7583. Min Act: -0.0001

Data Index: 894820 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.7224. Min Act: -0.0001

Data Index: 1297535 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.6818. Min Act: -0.0001

Data Index: 397801 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.6657. Min Act: -0.0001

Data Index: 1052366 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.6459. Min Act: -0.0001

Data Index: 1233125 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.8941. Min Act: -0.0001

Data Index: 174390 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.4545. Min Act: -0.0001

Data Index: 1026291 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.6012. Min Act: -0.0001

Data Index: 22966 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.5702. Min Act: -0.0001

Data Index: 503084 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.4004. Min Act: -0.0001

Data Index: 1029203 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.4537. Min Act: -0.0001

Data Index: 529334 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.3243. Min Act: -0.0001

Data Index: 738249 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 3.3667. Min Range: -3.3667

Max Act: 2.4335. Min Act: -0.0001

Data Index: 258184 (C4 (Web Text))

Max Activating Token Index: 885