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

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

Neuron 3957 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.5458. Min Act: -0.0000

Data Index: 1605380 (Python Code)

Max Activating Token Index: 573

Text #1

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.7097. Min Act: -0.0000

Data Index: 1489925 (Python Code)

Max Activating Token Index: 478

Text #2

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.4015. Min Act: -0.0000

Data Index: 1463451 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.3628. Min Act: -0.0000

Data Index: 1560428 (Python Code)

Max Activating Token Index: 334

Text #4

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.3300. Min Act: -0.0000

Data Index: 1514289 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.2964. Min Act: -0.0000

Data Index: 1493129 (Python Code)

Max Activating Token Index: 378

Text #6

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.2674. Min Act: -0.0000

Data Index: 1435640 (Python Code)

Max Activating Token Index: 431

Text #7

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.3938. Min Act: -0.0000

Data Index: 1474599 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.2263. Min Act: -0.0000

Data Index: 1654179 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.2099. Min Act: -0.0000

Data Index: 1439535 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.0579. Min Act: -0.0000

Data Index: 467730 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.0903. Min Act: -0.0000

Data Index: 1493246 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.1036. Min Act: -0.0000

Data Index: 1502201 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 3.7097. Min Range: -3.7097

Max Act: 2.8973. Min Act: -0.0000

Data Index: 1464912 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.0876. Min Act: -0.0000

Data Index: 1617594 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 3.7097. Min Range: -3.7097

Max Act: 2.7929. Min Act: -0.0000

Data Index: 1463707 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 3.7097. Min Range: -3.7097

Max Act: 3.0601. Min Act: -0.0000

Data Index: 1366127 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 3.7097. Min Range: -3.7097

Max Act: 2.9133. Min Act: -0.0000

Data Index: 1514462 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 3.7097. Min Range: -3.7097

Max Act: 2.8297. Min Act: -0.0000

Data Index: 1415298 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 3.7097. Min Range: -3.7097

Max Act: 2.8032. Min Act: -0.0000

Data Index: 1377943 (Python Code)

Max Activating Token Index: 462