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

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

Neuron 72 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2070. Min Range: -2.2070

Max Act: 2.2070. Min Act: -0.0000

Data Index: 99342 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 2.2070. Min Range: -2.2070

Max Act: 1.3470. Min Act: -0.0000

Data Index: 928795 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 2.2070. Min Range: -2.2070

Max Act: 1.2415. Min Act: -0.0000

Data Index: 976639 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 2.2070. Min Range: -2.2070

Max Act: 1.3050. Min Act: -0.0000

Data Index: 966485 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 2.2070. Min Range: -2.2070

Max Act: 1.1493. Min Act: -0.0000

Data Index: 435069 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 2.2070. Min Range: -2.2070

Max Act: 1.0792. Min Act: -0.0000

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.9739. Min Act: -0.0000

Data Index: 189932 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.9987. Min Act: -0.0000

Data Index: 398621 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1331655 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.9460. Min Act: -0.0000

Data Index: 745445 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.9071. Min Act: -0.0000

Data Index: 692116 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.8240. Min Act: -0.0000

Data Index: 730104 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.8284. Min Act: -0.0000

Data Index: 665928 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1195672 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1157419 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.7751. Min Act: -0.0000

Data Index: 597606 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1214345 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1247457 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.7280. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 2.2070. Min Range: -2.2070

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1253604 (C4 (Web Text))

Max Activating Token Index: 603