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

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

Neuron 2667 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7906. Min Act: -0.0000

Data Index: 911320 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6911. Min Act: -0.0000

Data Index: 729952 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7211. Min Act: -0.0000

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6697. Min Act: -0.0000

Data Index: 529457 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.7072. Min Act: -0.0000

Data Index: 454621 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6102. Min Act: -0.0000

Data Index: 90161 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6114. Min Act: -0.0000

Data Index: 797329 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5976. Min Act: -0.0000

Data Index: 257666 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6206. Min Act: -0.0000

Data Index: 399452 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1628816 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5160. Min Act: -0.0000

Data Index: 273222 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5500. Min Act: -0.0000

Data Index: 790957 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5343. Min Act: -0.0000

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1402959 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5537. Min Act: -0.0000

Data Index: 258303 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1218216 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5655. Min Act: -0.0000

Data Index: 631183 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5215. Min Act: -0.0000

Data Index: 1506907 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1454893 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 0.7906. Min Range: -0.7906

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1497358 (Python Code)

Max Activating Token Index: 243