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

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

Neuron 3088 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.9502. Min Act: -0.0001

Data Index: 774618 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.6524. Min Act: -0.0001

Data Index: 830713 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.9374. Min Act: -0.0001

Data Index: 1074034 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8078. Min Act: -0.0001

Data Index: 735442 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.6621. Min Act: -0.0001

Data Index: 593184 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.8070. Min Act: -0.0001

Data Index: 1034893 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7814. Min Act: -0.0001

Data Index: 724602 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.4870. Min Act: -0.0001

Data Index: 1142963 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7131. Min Act: -0.0001

Data Index: 121499 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.5400. Min Act: -0.0001

Data Index: 1138312 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.6809. Min Act: -0.0001

Data Index: 3323 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.6518. Min Act: -0.0001

Data Index: 16078 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.6319. Min Act: -0.0001

Data Index: 976997 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.5092. Min Act: -0.0001

Data Index: 1329320 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.3497. Min Act: -0.0001

Data Index: 1136973 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.7321. Min Act: -0.0001

Data Index: 801394 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.3806. Min Act: -0.0001

Data Index: 60117 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.3902. Min Act: -0.0001

Data Index: 1289643 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.3792. Min Act: -0.0001

Data Index: 1105804 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 3.9502. Min Range: -3.9502

Max Act: 3.4972. Min Act: -0.0001

Data Index: 858283 (C4 (Web Text))

Max Activating Token Index: 953