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

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

Neuron 3886 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: 0.8158. Min Range: -0.8158

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1238324 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1045802 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5813. Min Act: -0.0000

Data Index: 641494 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5446. Min Act: -0.0000

Data Index: 825463 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5427. Min Act: -0.0000

Data Index: 47672 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.4427. Min Act: -0.0000

Data Index: 776050 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1428452 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.4905. Min Act: -0.0000

Data Index: 772213 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5545. Min Act: -0.0001

Data Index: 1005389 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1261646 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.3418. Min Act: -0.0001

Data Index: 654435 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.2185. Min Act: -0.0001

Data Index: 320908 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.3272. Min Act: -0.0000

Data Index: 307059 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.2777. Min Act: -0.0000

Data Index: 474398 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.2234. Min Act: -0.0000

Data Index: 296627 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.2110. Min Act: -0.0001

Data Index: 441852 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.1860. Min Act: -0.0001

Data Index: 730508 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1235210 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.1448. Min Act: -0.0000

Data Index: 428685 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1040240 (C4 (Web Text))

Max Activating Token Index: 791