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

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

Neuron 1200 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: 2.2033. Min Range: -2.2033

Max Act: 2.2033. Min Act: -0.0000

Data Index: 1381183 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1512113 (Python Code)

Max Activating Token Index: 477

Text #2

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1184443 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.4651. Min Act: -0.0000

Data Index: 1172581 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3879. Min Act: -0.0000

Data Index: 992181 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.5154. Min Act: -0.0000

Data Index: 335323 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.4683. Min Act: -0.0000

Data Index: 486792 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.4427. Min Act: -0.0000

Data Index: 448312 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3205. Min Act: -0.0000

Data Index: 712980 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3902. Min Act: -0.0000

Data Index: 335075 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1380539 (Python Code)

Max Activating Token Index: 1011

Text #11

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1266383 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3245. Min Act: -0.0000

Data Index: 813235 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3280. Min Act: -0.0000

Data Index: 253743 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.0562. Min Act: -0.0000

Data Index: 876492 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.2353. Min Act: -0.0000

Data Index: 656469 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.2530. Min Act: -0.0000

Data Index: 354212 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.4661. Min Act: -0.0000

Data Index: 522125 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.3725. Min Act: -0.0000

Data Index: 589271 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 2.2033. Min Range: -2.2033

Max Act: 1.2861. Min Act: -0.0000

Data Index: 945443 (C4 (Web Text))

Max Activating Token Index: 813