Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 73 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7942. Min Act: -0.0003

Data Index: 1655877 (Python Code)

Max Activating Token Index: 277

Text #1

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7900. Min Act: -0.0003

Data Index: 1567699 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7421. Min Act: -0.0003

Data Index: 88602 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7565. Min Act: -0.0003

Data Index: 1630860 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6601. Min Act: -0.0003

Data Index: 1427022 (Python Code)

Max Activating Token Index: 82

Text #5

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6559. Min Act: -0.0003

Data Index: 1470290 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6334. Min Act: -0.0003

Data Index: 1530672 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.5977. Min Act: -0.0003

Data Index: 1575983 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6604. Min Act: -0.0003

Data Index: 1596218 (Python Code)

Max Activating Token Index: 112

Text #9

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6118. Min Act: -0.0003

Data Index: 956125 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6145. Min Act: -0.0003

Data Index: 1540748 (Python Code)

Max Activating Token Index: 337

Text #11

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6275. Min Act: -0.0003

Data Index: 1484316 (Python Code)

Max Activating Token Index: 831

Text #12

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6280. Min Act: -0.0003

Data Index: 1568570 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6043. Min Act: -0.0003

Data Index: 1643360 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6040. Min Act: -0.0003

Data Index: 1292389 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6114. Min Act: -0.0003

Data Index: 1371263 (Python Code)

Max Activating Token Index: 899

Text #16

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.5908. Min Act: -0.0003

Data Index: 460957 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6321. Min Act: -0.0003

Data Index: 1397401 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7544. Min Act: -0.0003

Data Index: 1229556 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6044. Min Act: -0.0003

Data Index: 1461990 (Python Code)

Max Activating Token Index: 3