Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1955 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.9046. Min Act: -0.0001

Data Index: 307846 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 7.0288. Min Range: -7.0288

Max Act: 7.0288. Min Act: -0.0001

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 7.0288. Min Range: -7.0288

Max Act: 6.8233. Min Act: -0.0001

Data Index: 1248127 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 7.0288. Min Range: -7.0288

Max Act: 6.0674. Min Act: -0.0001

Data Index: 247702 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.1751. Min Act: -0.0001

Data Index: 1101064 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.9177. Min Act: -0.0001

Data Index: 156605 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 7.0288. Min Range: -7.0288

Max Act: 6.2912. Min Act: -0.0001

Data Index: 1195402 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.5454. Min Act: -0.0001

Data Index: 795020 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.7318. Min Act: -0.0001

Data Index: 865948 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.5166. Min Act: -0.0001

Data Index: 1047667 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.9645. Min Act: -0.0001

Data Index: 1301349 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.5742. Min Act: -0.0001

Data Index: 941121 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.4396. Min Act: -0.0001

Data Index: 559618 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.3918. Min Act: -0.0001

Data Index: 723343 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.3742. Min Act: -0.0001

Data Index: 137547 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.2696. Min Act: -0.0001

Data Index: 166585 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 7.0288. Min Range: -7.0288

Max Act: 4.8266. Min Act: -0.0001

Data Index: 519356 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.3954. Min Act: -0.0000

Data Index: 840249 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.4654. Min Act: -0.0000

Data Index: 1327660 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 7.0288. Min Range: -7.0288

Max Act: 5.0077. Min Act: -0.0001

Data Index: 237071 (C4 (Web Text))

Max Activating Token Index: 860