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

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

Neuron 3158 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.4171. Min Act: -0.0000

Data Index: 944342 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1450778 (Python Code)

Max Activating Token Index: 424

Text #2

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1575525 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3192. Min Act: -0.0000

Data Index: 96005 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1638622 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1312395 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3150. Min Act: -0.0000

Data Index: 18017 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2907. Min Act: -0.0000

Data Index: 629621 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1464175 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3039. Min Act: -0.0000

Data Index: 565459 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2884. Min Act: -0.0000

Data Index: 742637 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2883. Min Act: -0.0000

Data Index: 85712 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1248815 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1633249 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3075. Min Act: -0.0001

Data Index: 339843 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.3002. Min Act: -0.0000

Data Index: 471381 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2816. Min Act: -0.0000

Data Index: 329027 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2897. Min Act: -0.0001

Data Index: 27280 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2956. Min Act: -0.0001

Data Index: 163255 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.4171. Min Range: -0.4171

Max Act: 0.2883. Min Act: -0.0001

Data Index: 530329 (C4 (Web Text))

Max Activating Token Index: 75