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

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

Neuron 1297 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: 0.7048. Min Range: -0.7048

Max Act: 0.7048. Min Act: -0.0000

Data Index: 380611 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6288. Min Act: -0.0000

Data Index: 562755 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5907. Min Act: -0.0000

Data Index: 215208 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5916. Min Act: -0.0000

Data Index: 174602 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5172. Min Act: -0.0000

Data Index: 30160 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5276. Min Act: -0.0000

Data Index: 6265 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5216. Min Act: -0.0000

Data Index: 97042 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1166511 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1166060 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1042315 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1272130 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5082. Min Act: -0.0000

Data Index: 727865 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4803. Min Act: -0.0000

Data Index: 84111 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4638. Min Act: -0.0000

Data Index: 564996 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1256567 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1215795 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4755. Min Act: -0.0000

Data Index: 652183 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4439. Min Act: -0.0000

Data Index: 760181 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1062940 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4084. Min Act: -0.0000

Data Index: 792726 (C4 (Web Text))

Max Activating Token Index: 166