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

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

Neuron 3803 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1442685 (Python Code)

Max Activating Token Index: 716

Text #1

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5392. Min Act: -0.0001

Data Index: 1557186 (Python Code)

Max Activating Token Index: 399

Text #2

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5632. Min Act: -0.0001

Data Index: 1177246 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5263. Min Act: -0.0001

Data Index: 1408149 (Python Code)

Max Activating Token Index: 760

Text #4

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1479142 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5310. Min Act: -0.0001

Data Index: 1435887 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1617342 (Python Code)

Max Activating Token Index: 784

Text #7

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5235. Min Act: -0.0001

Data Index: 1462971 (Python Code)

Max Activating Token Index: 531

Text #8

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5046. Min Act: -0.0001

Data Index: 1438421 (Python Code)

Max Activating Token Index: 581

Text #9

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4905. Min Act: -0.0001

Data Index: 1642549 (Python Code)

Max Activating Token Index: 305

Text #10

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5101. Min Act: -0.0001

Data Index: 1654376 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5278. Min Act: -0.0000

Data Index: 757424 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4679. Min Act: -0.0001

Data Index: 1482745 (Python Code)

Max Activating Token Index: 299

Text #13

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4567. Min Act: -0.0001

Data Index: 1534348 (Python Code)

Max Activating Token Index: 564

Text #14

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.5033. Min Act: -0.0001

Data Index: 1424529 (Python Code)

Max Activating Token Index: 763

Text #15

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1622114 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4929. Min Act: -0.0001

Data Index: 1450813 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1433290 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4751. Min Act: -0.0001

Data Index: 1424808 (Python Code)

Max Activating Token Index: 576

Text #19

Max Range: 0.5980. Min Range: -0.5980

Max Act: 0.4741. Min Act: -0.0001

Data Index: 565094 (C4 (Web Text))

Max Activating Token Index: 78