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

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

Neuron 530 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.8553. Min Act: 0.0000

Data Index: 785210 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.7504. Min Act: -0.0000

Data Index: 211759 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.5627. Min Act: -0.0000

Data Index: 1288760 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.5697. Min Act: -0.0001

Data Index: 1281616 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1248359 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2327. Min Act: -0.0000

Data Index: 533502 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2461. Min Act: -0.0000

Data Index: 14725 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.3499. Min Act: -0.0001

Data Index: 1241259 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1299761 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2129. Min Act: -0.0000

Data Index: 895681 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2364. Min Act: -0.0000

Data Index: 212631 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1981. Min Act: -0.0000

Data Index: 498606 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1123449 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1817. Min Act: -0.0001

Data Index: 849314 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2531. Min Act: -0.0000

Data Index: 437898 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1294355 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.9734. Min Act: -0.0000

Data Index: 178023 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.2587. Min Act: -0.0000

Data Index: 163869 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.8553. Min Range: -1.8553

Max Act: 0.7253. Min Act: -0.0000

Data Index: 283483 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 1.8553. Min Range: -1.8553

Max Act: 1.1841. Min Act: -0.0000

Data Index: 255111 (C4 (Web Text))

Max Activating Token Index: 615