Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4838 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1487908 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3334. Min Act: -0.0001

Data Index: 1599904 (Python Code)

Max Activating Token Index: 137

Text #2

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1382222 (Python Code)

Max Activating Token Index: 126

Text #3

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3182. Min Act: -0.0001

Data Index: 1645093 (Python Code)

Max Activating Token Index: 159

Text #4

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1573781 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1648522 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3036. Min Act: -0.0001

Data Index: 1442298 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2969. Min Act: -0.0001

Data Index: 1643001 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1497570 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1652526 (Python Code)

Max Activating Token Index: 173

Text #10

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1633130 (Python Code)

Max Activating Token Index: 198

Text #11

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1555727 (Python Code)

Max Activating Token Index: 218

Text #12

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1423840 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3068. Min Act: -0.0001

Data Index: 1629827 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1436950 (Python Code)

Max Activating Token Index: 135

Text #15

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1488384 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2917. Min Act: -0.0001

Data Index: 1428398 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2722. Min Act: -0.0001

Data Index: 1627088 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2670. Min Act: -0.0001

Data Index: 1605057 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1623024 (Python Code)

Max Activating Token Index: 71