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

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

Neuron 4273 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.8373. Min Act: -0.0001

Data Index: 928791 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.8552. Min Act: -0.0001

Data Index: 1096056 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7118. Min Act: -0.0001

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.6605. Min Act: -0.0001

Data Index: 805023 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7539. Min Act: -0.0001

Data Index: 775259 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.5563. Min Act: -0.0001

Data Index: 743628 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.7454. Min Act: -0.0001

Data Index: 68000 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.5394. Min Act: -0.0001

Data Index: 1584471 (Python Code)

Max Activating Token Index: 916

Text #8

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.4624. Min Act: -0.0001

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.4936. Min Act: -0.0001

Data Index: 963087 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.4201. Min Act: -0.0001

Data Index: 593049 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.5680. Min Act: -0.0001

Data Index: 1547764 (Python Code)

Max Activating Token Index: 198

Text #12

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.3960. Min Act: -0.0001

Data Index: 820457 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.4042. Min Act: -0.0001

Data Index: 1185530 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.3269. Min Act: -0.0001

Data Index: 1516095 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.5727. Min Act: -0.0001

Data Index: 631958 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.2574. Min Act: -0.0001

Data Index: 782664 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.4531. Min Act: -0.0001

Data Index: 1292151 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.5540. Min Act: -0.0001

Data Index: 280995 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.8552. Min Range: -1.8552

Max Act: 1.4187. Min Act: -0.0001

Data Index: 588233 (C4 (Web Text))

Max Activating Token Index: 250