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

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

Neuron 2022 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4863. Min Range: -1.4863

Max Act: 1.4863. Min Act: -0.0002

Data Index: 287441 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.8963. Min Act: -0.0001

Data Index: 1308443 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.9555. Min Act: -0.0002

Data Index: 815364 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.9261. Min Act: -0.0002

Data Index: 805694 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.8218. Min Act: -0.0001

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7519. Min Act: -0.0001

Data Index: 1143151 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7742. Min Act: -0.0001

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7593. Min Act: -0.0001

Data Index: 365517 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7402. Min Act: -0.0001

Data Index: 1240908 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.8383. Min Act: -0.0001

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7480. Min Act: -0.0002

Data Index: 156930 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.8337. Min Act: -0.0001

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7536. Min Act: -0.0001

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7501. Min Act: -0.0002

Data Index: 1110031 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7674. Min Act: -0.0001

Data Index: 437136 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7183. Min Act: -0.0001

Data Index: 1170364 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7416. Min Act: -0.0001

Data Index: 118536 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1111332 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.7557. Min Act: -0.0002

Data Index: 452636 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.4863. Min Range: -1.4863

Max Act: 0.6690. Min Act: -0.0001

Data Index: 161291 (C4 (Web Text))

Max Activating Token Index: 222