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

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

Neuron 2779 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: 0.6299. Min Range: -0.6299

Max Act: 0.6299. Min Act: -0.0000

Data Index: 937161 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4955. Min Act: -0.0001

Data Index: 221023 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4843. Min Act: -0.0000

Data Index: 205329 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1218592 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4619. Min Act: -0.0001

Data Index: 775088 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4965. Min Act: -0.0001

Data Index: 210164 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.5191. Min Act: -0.0001

Data Index: 402811 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1098351 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4512. Min Act: -0.0000

Data Index: 612473 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4401. Min Act: -0.0000

Data Index: 988519 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1178863 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4255. Min Act: -0.0001

Data Index: 1022951 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.3917. Min Act: -0.0000

Data Index: 660955 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1040554 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.4022. Min Act: -0.0000

Data Index: 365760 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.3871. Min Act: -0.0001

Data Index: 725114 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1185915 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.3631. Min Act: -0.0000

Data Index: 893290 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1113255 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.6299. Min Range: -0.6299

Max Act: 0.3547. Min Act: -0.0000

Data Index: 186952 (C4 (Web Text))

Max Activating Token Index: 370