Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3003 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.2198. Min Range: -4.2198

Max Act: 4.2198. Min Act: -0.0001

Data Index: 838372 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 4.2198. Min Range: -4.2198

Max Act: 4.1547. Min Act: -0.0001

Data Index: 810046 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 4.2198. Min Range: -4.2198

Max Act: 3.4959. Min Act: -0.0001

Data Index: 426931 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 4.2198. Min Range: -4.2198

Max Act: 3.1857. Min Act: -0.0001

Data Index: 133130 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 4.2198. Min Range: -4.2198

Max Act: 3.1484. Min Act: -0.0001

Data Index: 784458 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 4.2198. Min Range: -4.2198

Max Act: 3.0817. Min Act: -0.0001

Data Index: 69790 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 4.2198. Min Range: -4.2198

Max Act: 3.0121. Min Act: -0.0001

Data Index: 400363 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 4.2198. Min Range: -4.2198

Max Act: 3.0057. Min Act: -0.0001

Data Index: 264556 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.7735. Min Act: -0.0001

Data Index: 1279273 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.9093. Min Act: -0.0001

Data Index: 869711 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 4.2198. Min Range: -4.2198

Max Act: 3.0157. Min Act: -0.0001

Data Index: 864377 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.8687. Min Act: -0.0001

Data Index: 338576 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.8451. Min Act: -0.0001

Data Index: 1213757 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.9792. Min Act: -0.0001

Data Index: 292962 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.6967. Min Act: -0.0001

Data Index: 676548 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.9297. Min Act: -0.0001

Data Index: 213686 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.9321. Min Act: -0.0001

Data Index: 122551 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.7947. Min Act: -0.0001

Data Index: 1049112 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.7816. Min Act: -0.0001

Data Index: 206064 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 4.2198. Min Range: -4.2198

Max Act: 2.6387. Min Act: -0.0001

Data Index: 62693 (C4 (Web Text))

Max Activating Token Index: 963