Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2636 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1400577 (Python Code)

Max Activating Token Index: 742

Text #1

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3390. Min Act: -0.0000

Data Index: 406931 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1398657 (Python Code)

Max Activating Token Index: 738

Text #3

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3395. Min Act: -0.0000

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1650545 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3196. Min Act: -0.0000

Data Index: 986943 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3166. Min Act: -0.0000

Data Index: 54075 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1021582 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2954. Min Act: -0.0000

Data Index: 439923 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2980. Min Act: -0.0000

Data Index: 935000 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2804. Min Act: -0.0000

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2699. Min Act: -0.0000

Data Index: 433748 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1243927 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2890. Min Act: -0.0000

Data Index: 510189 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2686. Min Act: -0.0000

Data Index: 938167 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2914. Min Act: -0.0000

Data Index: 888744 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2743. Min Act: -0.0000

Data Index: 556335 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1097618 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2745. Min Act: -0.0000

Data Index: 116153 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2871. Min Act: -0.0000

Data Index: 925497 (C4 (Web Text))

Max Activating Token Index: 181