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

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

Neuron 4757 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: 1.8065. Min Range: -1.8065

Max Act: 1.7097. Min Act: -0.0000

Data Index: 153931 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.7254. Min Act: -0.0000

Data Index: 668072 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.8065. Min Act: -0.0000

Data Index: 663236 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.6965. Min Act: -0.0000

Data Index: 242812 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.6296. Min Act: -0.0000

Data Index: 835578 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4158. Min Act: -0.0000

Data Index: 596383 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.6565. Min Act: -0.0001

Data Index: 627022 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.6349. Min Act: -0.0000

Data Index: 590327 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4463. Min Act: -0.0000

Data Index: 306326 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4733. Min Act: -0.0000

Data Index: 1353716 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.5270. Min Act: -0.0000

Data Index: 109046 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4291. Min Act: -0.0000

Data Index: 184926 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4969. Min Act: -0.0000

Data Index: 636148 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4458. Min Act: -0.0000

Data Index: 58306 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4488. Min Act: -0.0000

Data Index: 555086 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.3231. Min Act: -0.0000

Data Index: 1092277 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.2723. Min Act: -0.0000

Data Index: 68470 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.3347. Min Act: -0.0000

Data Index: 329263 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.4045. Min Act: -0.0000

Data Index: 367178 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 1.8065. Min Range: -1.8065

Max Act: 1.3676. Min Act: -0.0000

Data Index: 510655 (C4 (Web Text))

Max Activating Token Index: 487