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

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

Neuron 2798 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.5774. Min Act: -0.0000

Data Index: 892017 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1066890 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.5223. Min Act: -0.0000

Data Index: 987490 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4790. Min Act: -0.0000

Data Index: 799244 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1168233 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1329996 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4130. Min Act: -0.0000

Data Index: 419812 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1273367 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1641679 (Python Code)

Max Activating Token Index: 530

Text #9

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4219. Min Act: -0.0000

Data Index: 809230 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4629. Min Act: -0.0000

Data Index: 103529 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1370235 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1229456 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1608518 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1118729 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1400719 (Python Code)

Max Activating Token Index: 124

Text #16

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1413786 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1649420 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.4352. Min Act: -0.0000

Data Index: 477413 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.5774. Min Range: -0.5774

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1385240 (Python Code)

Max Activating Token Index: 243