Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 35 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3703. Min Act: -0.0001

Data Index: 76581 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3826. Min Act: -0.0001

Data Index: 15276 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3651. Min Act: -0.0001

Data Index: 708987 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3624. Min Act: -0.0001

Data Index: 810340 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3642. Min Act: -0.0001

Data Index: 638661 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1301349 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3397. Min Act: -0.0001

Data Index: 749778 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3474. Min Act: -0.0001

Data Index: 598989 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3450. Min Act: -0.0001

Data Index: 650885 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3282. Min Act: -0.0001

Data Index: 984663 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3100. Min Act: -0.0001

Data Index: 598110 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1340658 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1330193 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3153. Min Act: -0.0001

Data Index: 376319 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3122. Min Act: -0.0001

Data Index: 264023 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1043435 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3129. Min Act: -0.0001

Data Index: 815408 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1283274 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1233564 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.3826. Min Range: -0.3826

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1150470 (C4 (Web Text))

Max Activating Token Index: 960