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

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

Neuron 373 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: 0.4397. Min Range: -0.4397

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1515451 (Python Code)

Max Activating Token Index: 899

Text #1

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1529032 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1628570 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1474937 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1392943 (Python Code)

Max Activating Token Index: 260

Text #5

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1540964 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3666. Min Act: -0.0001

Data Index: 1388948 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3661. Min Act: -0.0001

Data Index: 1648489 (Python Code)

Max Activating Token Index: 871

Text #8

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1427838 (Python Code)

Max Activating Token Index: 636

Text #9

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1556434 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3786. Min Act: -0.0001

Data Index: 1653721 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1640721 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3472. Min Act: -0.0001

Data Index: 1525642 (Python Code)

Max Activating Token Index: 733

Text #13

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3319. Min Act: -0.0000

Data Index: 1609288 (Python Code)

Max Activating Token Index: 887

Text #14

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3315. Min Act: -0.0001

Data Index: 1581608 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1430199 (Python Code)

Max Activating Token Index: 473

Text #16

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1533237 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1481852 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1458424 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1608205 (Python Code)

Max Activating Token Index: 763