Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1858 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.4225. Min Act: -0.0003

Data Index: 1483561 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3786. Min Act: -0.0003

Data Index: 222417 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3670. Min Act: -0.0003

Data Index: 1465915 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3525. Min Act: -0.0003

Data Index: 1449391 (Python Code)

Max Activating Token Index: 626

Text #4

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3449. Min Act: -0.0003

Data Index: 1473118 (Python Code)

Max Activating Token Index: 584

Text #5

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3505. Min Act: -0.0003

Data Index: 1516432 (Python Code)

Max Activating Token Index: 247

Text #6

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3422. Min Act: -0.0003

Data Index: 1421034 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3515. Min Act: -0.0003

Data Index: 1583878 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3611. Min Act: -0.0003

Data Index: 1529324 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3489. Min Act: -0.0003

Data Index: 1442138 (Python Code)

Max Activating Token Index: 426

Text #10

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3079. Min Act: -0.0003

Data Index: 445243 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3475. Min Act: -0.0003

Data Index: 1556394 (Python Code)

Max Activating Token Index: 299

Text #12

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3493. Min Act: -0.0003

Data Index: 1404229 (Python Code)

Max Activating Token Index: 733

Text #13

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3464. Min Act: -0.0003

Data Index: 1631465 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3451. Min Act: -0.0003

Data Index: 1367740 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3510. Min Act: -0.0003

Data Index: 1473402 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3383. Min Act: -0.0003

Data Index: 1601607 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3328. Min Act: -0.0003

Data Index: 1646803 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3449. Min Act: -0.0003

Data Index: 1596750 (Python Code)

Max Activating Token Index: 599

Text #19

Max Range: 0.4225. Min Range: -0.4225

Max Act: 0.3338. Min Act: -0.0003

Data Index: 1468936 (Python Code)

Max Activating Token Index: 339