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

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

Neuron 1053 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: 3.7169. Min Range: -3.7169

Max Act: 3.7169. Min Act: -0.0001

Data Index: 673910 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.5551. Min Act: -0.0001

Data Index: 789364 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.6579. Min Act: -0.0001

Data Index: 644502 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.6494. Min Act: -0.0001

Data Index: 325940 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.7095. Min Act: -0.0001

Data Index: 148772 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.5071. Min Act: -0.0001

Data Index: 337453 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.1915. Min Act: -0.0001

Data Index: 819502 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.2891. Min Act: -0.0001

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.1366. Min Act: -0.0001

Data Index: 168944 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.2810. Min Act: -0.0001

Data Index: 1239856 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.2252. Min Act: -0.0001

Data Index: 715248 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.0286. Min Act: -0.0001

Data Index: 1257276 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.0225. Min Act: -0.0001

Data Index: 616197 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.7169. Min Range: -3.7169

Max Act: 2.9547. Min Act: -0.0001

Data Index: 1089775 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.0124. Min Act: -0.0001

Data Index: 392711 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 3.7169. Min Range: -3.7169

Max Act: 2.9165. Min Act: -0.0001

Data Index: 346323 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.1890. Min Act: -0.0001

Data Index: 1197844 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.0502. Min Act: -0.0001

Data Index: 299471 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.0247. Min Act: -0.0001

Data Index: 983152 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 3.7169. Min Range: -3.7169

Max Act: 3.1551. Min Act: -0.0001

Data Index: 597817 (C4 (Web Text))

Max Activating Token Index: 97