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

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

Neuron 2894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4787. Min Act: -0.0001

Data Index: 1149242 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4732. Min Act: -0.0001

Data Index: 898416 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4449. Min Act: -0.0001

Data Index: 211242 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4362. Min Act: -0.0001

Data Index: 1239508 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4520. Min Act: -0.0001

Data Index: 717557 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4047. Min Act: -0.0001

Data Index: 1173492 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4022. Min Act: -0.0001

Data Index: 426268 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3826. Min Act: -0.0001

Data Index: 1387533 (Python Code)

Max Activating Token Index: 96

Text #8

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3975. Min Act: -0.0001

Data Index: 319466 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3911. Min Act: -0.0001

Data Index: 89659 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3498. Min Act: -0.0001

Data Index: 287137 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3513. Min Act: -0.0001

Data Index: 445662 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3488. Min Act: -0.0001

Data Index: 159775 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1326912 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3354. Min Act: -0.0001

Data Index: 280742 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3422. Min Act: -0.0001

Data Index: 244395 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3325. Min Act: -0.0001

Data Index: 157728 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3332. Min Act: -0.0001

Data Index: 857666 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3182. Min Act: -0.0001

Data Index: 141496 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3390. Min Act: -0.0001

Data Index: 1100680 (C4 (Web Text))

Max Activating Token Index: 162