Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3418 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.8899. Min Act: -0.0001

Data Index: 23678 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.8295. Min Act: -0.0001

Data Index: 371042 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4535. Min Act: -0.0001

Data Index: 763368 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4282. Min Act: -0.0001

Data Index: 633169 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.4133. Min Act: -0.0001

Data Index: 1202676 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.3863. Min Act: -0.0001

Data Index: 361101 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.3037. Min Act: -0.0001

Data Index: 375578 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2734. Min Act: -0.0001

Data Index: 258546 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2181. Min Act: -0.0001

Data Index: 549806 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2816. Min Act: -0.0001

Data Index: 1234451 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2386. Min Act: -0.0001

Data Index: 463822 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2329. Min Act: -0.0001

Data Index: 1501165 (Python Code)

Max Activating Token Index: 172

Text #12

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2968. Min Act: -0.0001

Data Index: 1147098 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.1955. Min Act: -0.0001

Data Index: 1270314 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2137. Min Act: -0.0001

Data Index: 278385 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2158. Min Act: -0.0001

Data Index: 133046 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2182. Min Act: -0.0001

Data Index: 146808 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.2139. Min Act: -0.0001

Data Index: 862316 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.1698. Min Act: -0.0001

Data Index: 1234866 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.8899. Min Range: -1.8899

Max Act: 1.1967. Min Act: -0.0001

Data Index: 869774 (C4 (Web Text))

Max Activating Token Index: 23