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

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

Neuron 3401 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.4575. Min Act: -0.0001

Data Index: 710978 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.3385. Min Act: -0.0001

Data Index: 1075067 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.3704. Min Act: -0.0001

Data Index: 1117359 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.2180. Min Act: -0.0001

Data Index: 666277 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.2062. Min Act: -0.0001

Data Index: 1312761 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1900. Min Act: -0.0001

Data Index: 813461 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.3229. Min Act: -0.0001

Data Index: 1560692 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1043. Min Act: -0.0001

Data Index: 391416 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.2654. Min Act: -0.0001

Data Index: 577841 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1244. Min Act: -0.0001

Data Index: 1346859 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1120. Min Act: -0.0001

Data Index: 1365480 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.2279. Min Act: -0.0001

Data Index: 1602875 (Python Code)

Max Activating Token Index: 268

Text #12

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1374. Min Act: -0.0001

Data Index: 771527 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1179. Min Act: -0.0001

Data Index: 255828 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.1773. Min Act: -0.0001

Data Index: 508557 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.0455. Min Act: -0.0001

Data Index: 827220 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.0365. Min Act: -0.0001

Data Index: 558068 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.0889. Min Act: -0.0001

Data Index: 716023 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.0119. Min Act: -0.0001

Data Index: 1311117 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 1.4575. Min Range: -1.4575

Max Act: 1.0622. Min Act: -0.0001

Data Index: 1605000 (Python Code)

Max Activating Token Index: 1022