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

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

Neuron 5079 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0001

Data Index: 1656423 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1580626 (Python Code)

Max Activating Token Index: 686

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0001

Data Index: 1349678 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1553099 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0001

Data Index: 1327840 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0085. Min Act: -0.0001

Data Index: 1324160 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0085. Min Act: -0.0001

Data Index: 1516107 (Python Code)

Max Activating Token Index: 412

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0001

Data Index: 360119 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0001

Data Index: 736657 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0001

Data Index: 1553325 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1460176 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0085. Min Act: -0.0001

Data Index: 61766 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0001

Data Index: 836284 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0001

Data Index: 790293 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0001

Data Index: 1149762 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0001

Data Index: 1619267 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0001

Data Index: 1182626 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0001

Data Index: 1575932 (Python Code)

Max Activating Token Index: 273

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0001

Data Index: 1446987 (Python Code)

Max Activating Token Index: 367

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0001

Data Index: 977961 (C4 (Web Text))

Max Activating Token Index: 566