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

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

Neuron 2055 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: 0.5110. Min Range: -0.5110

Max Act: 0.4830. Min Act: -0.0001

Data Index: 712260 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.5110. Min Act: -0.0001

Data Index: 1018536 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.5073. Min Act: -0.0001

Data Index: 905565 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4438. Min Act: -0.0001

Data Index: 175116 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1596296 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4364. Min Act: -0.0000

Data Index: 312283 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4496. Min Act: -0.0000

Data Index: 772937 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1171578 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4383. Min Act: -0.0001

Data Index: 130044 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4316. Min Act: -0.0000

Data Index: 617294 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4452. Min Act: -0.0001

Data Index: 1162915 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1445527 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4305. Min Act: -0.0001

Data Index: 539298 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4254. Min Act: -0.0001

Data Index: 1567699 (Python Code)

Max Activating Token Index: 590

Text #14

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4535. Min Act: -0.0001

Data Index: 938618 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4233. Min Act: -0.0001

Data Index: 1125436 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4062. Min Act: -0.0001

Data Index: 1627477 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1547156 (Python Code)

Max Activating Token Index: 599

Text #18

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4400. Min Act: -0.0001

Data Index: 255112 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4250. Min Act: -0.0001

Data Index: 106064 (C4 (Web Text))

Max Activating Token Index: 360