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

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

Neuron 3789 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4304. Min Act: -0.0000

Data Index: 976284 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4034. Min Act: -0.0000

Data Index: 888375 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.4088. Min Act: -0.0001

Data Index: 672359 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3794. Min Act: -0.0000

Data Index: 68536 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3740. Min Act: -0.0000

Data Index: 714113 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3546. Min Act: -0.0001

Data Index: 702944 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3714. Min Act: -0.0001

Data Index: 606287 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3376. Min Act: -0.0001

Data Index: 842283 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3563. Min Act: -0.0001

Data Index: 5360 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3161. Min Act: -0.0001

Data Index: 864139 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3106. Min Act: -0.0001

Data Index: 854929 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3132. Min Act: -0.0000

Data Index: 530681 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3166. Min Act: -0.0001

Data Index: 804902 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3104. Min Act: -0.0000

Data Index: 908107 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3378. Min Act: -0.0001

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3039. Min Act: -0.0000

Data Index: 304208 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3045. Min Act: -0.0001

Data Index: 585518 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3053. Min Act: -0.0000

Data Index: 469919 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1196262 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.4304. Min Range: -0.4304

Max Act: 0.3142. Min Act: -0.0001

Data Index: 463196 (C4 (Web Text))

Max Activating Token Index: 363