Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5626 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.8105. Min Act: -0.0000

Data Index: 1165620 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.7920. Min Act: -0.0000

Data Index: 65892 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1132493 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.4670. Min Act: -0.0000

Data Index: 1143904 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1234232 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3922. Min Act: -0.0000

Data Index: 309985 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.5616. Min Act: 0.0000

Data Index: 1173522 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.5566. Min Act: -0.0000

Data Index: 632644 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.4416. Min Act: -0.0000

Data Index: 121791 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3997. Min Act: -0.0000

Data Index: 440491 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3739. Min Act: -0.0000

Data Index: 1020074 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3670. Min Act: -0.0000

Data Index: 1182126 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2817. Min Act: -0.0000

Data Index: 439742 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3484. Min Act: -0.0000

Data Index: 231232 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1211456 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3073. Min Act: -0.0000

Data Index: 680762 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1066071 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2370. Min Act: -0.0000

Data Index: 51177 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1294429 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.8105. Min Range: -1.8105

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1287141 (C4 (Web Text))

Max Activating Token Index: 716