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

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

Neuron 2017 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4120. Min Range: -2.4120

Max Act: 2.4120. Min Act: -0.0000

Data Index: 1620584 (Python Code)

Max Activating Token Index: 242

Text #1

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.9696. Min Act: -0.0000

Data Index: 1644918 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 2.4120. Min Range: -2.4120

Max Act: 2.1178. Min Act: -0.0000

Data Index: 1470336 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.9326. Min Act: -0.0000

Data Index: 1643343 (Python Code)

Max Activating Token Index: 17

Text #4

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1644046 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1626711 (Python Code)

Max Activating Token Index: 441

Text #6

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.6161. Min Act: -0.0000

Data Index: 1458205 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.4920. Min Act: -0.0000

Data Index: 1527428 (Python Code)

Max Activating Token Index: 92

Text #8

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.6382. Min Act: -0.0000

Data Index: 1606496 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.3934. Min Act: -0.0000

Data Index: 1628615 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.3238. Min Act: -0.0000

Data Index: 1159621 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1585560 (Python Code)

Max Activating Token Index: 151

Text #12

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.3151. Min Act: -0.0000

Data Index: 1459392 (Python Code)

Max Activating Token Index: 904

Text #13

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1655652 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.3419. Min Act: -0.0000

Data Index: 598027 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1652128 (Python Code)

Max Activating Token Index: 985

Text #16

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1448152 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.3129. Min Act: -0.0000

Data Index: 1397925 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.2219. Min Act: -0.0000

Data Index: 478569 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 2.4120. Min Range: -2.4120

Max Act: 1.1393. Min Act: -0.0000

Data Index: 614134 (C4 (Web Text))

Max Activating Token Index: 591