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

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

Neuron 1127 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.1250. Min Act: -0.0000

Data Index: 544738 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.1161. Min Act: -0.0001

Data Index: 1321580 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.1250. Min Range: -1.1250

Max Act: 1.0225. Min Act: -0.0000

Data Index: 244634 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9086. Min Act: -0.0000

Data Index: 126991 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.9107. Min Act: -0.0000

Data Index: 528926 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8532. Min Act: -0.0001

Data Index: 218233 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8751. Min Act: -0.0001

Data Index: 1264352 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8683. Min Act: -0.0001

Data Index: 978891 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8414. Min Act: -0.0001

Data Index: 204418 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8916. Min Act: -0.0001

Data Index: 807708 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8375. Min Act: -0.0001

Data Index: 788207 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.7945. Min Act: -0.0001

Data Index: 297720 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.7980. Min Act: -0.0000

Data Index: 736329 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1078536 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.7585. Min Act: -0.0001

Data Index: 615906 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1265054 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1127896 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8478. Min Act: -0.0001

Data Index: 786940 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.8108. Min Act: -0.0001

Data Index: 318270 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 1.1250. Min Range: -1.1250

Max Act: 0.7632. Min Act: -0.0000

Data Index: 885418 (C4 (Web Text))

Max Activating Token Index: 729