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

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

Neuron 3649 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1545835 (Python Code)

Max Activating Token Index: 833

Text #1

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8965. Min Act: -0.0000

Data Index: 1338285 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.8249. Min Act: -0.0000

Data Index: 843756 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7583. Min Act: 0.0002

Data Index: 920202 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7363. Min Act: -0.0000

Data Index: 966765 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7456. Min Act: 0.0000

Data Index: 1231592 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.7279. Min Act: -0.0000

Data Index: 633203 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6893. Min Act: -0.0000

Data Index: 32460 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6318. Min Act: 0.0000

Data Index: 1422149 (Python Code)

Max Activating Token Index: 188

Text #9

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6212. Min Act: -0.0000

Data Index: 575699 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6545. Min Act: 0.0000

Data Index: 1430722 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.6052. Min Act: 0.0000

Data Index: 918175 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1646259 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5997. Min Act: 0.0000

Data Index: 1124174 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1383345 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5917. Min Act: -0.0000

Data Index: 722793 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5671. Min Act: 0.0000

Data Index: 1543836 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5819. Min Act: -0.0000

Data Index: 621882 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5689. Min Act: -0.0000

Data Index: 623121 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.8965. Min Range: -0.8965

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1140661 (C4 (Web Text))

Max Activating Token Index: 500