Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4868 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3798. Min Act: -0.0001

Data Index: 528825 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3543. Min Act: -0.0001

Data Index: 636289 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3312. Min Act: -0.0001

Data Index: 767392 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1279242 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3202. Min Act: -0.0001

Data Index: 1182472 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2920. Min Act: -0.0001

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3333. Min Act: -0.0000

Data Index: 537070 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2934. Min Act: -0.0000

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2987. Min Act: -0.0001

Data Index: 926247 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3189. Min Act: -0.0001

Data Index: 610116 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2954. Min Act: -0.0001

Data Index: 573045 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1152319 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2884. Min Act: -0.0001

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2786. Min Act: -0.0000

Data Index: 958185 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2802. Min Act: -0.0001

Data Index: 900380 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2775. Min Act: -0.0001

Data Index: 294774 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2713. Min Act: -0.0001

Data Index: 1282151 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2584. Min Act: -0.0001

Data Index: 662068 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2483. Min Act: -0.0001

Data Index: 135398 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.3798. Min Range: -0.3798

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1060678 (C4 (Web Text))

Max Activating Token Index: 978