Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3675 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.5842. Min Act: -0.0001

Data Index: 23676 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3661. Min Act: -0.0001

Data Index: 615557 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3364. Min Act: -0.0001

Data Index: 340590 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2084. Min Act: -0.0001

Data Index: 549061 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.0540. Min Act: -0.0001

Data Index: 339228 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.1306. Min Act: -0.0001

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.0923. Min Act: -0.0001

Data Index: 788107 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.0497. Min Act: -0.0001

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.0583. Min Act: -0.0001

Data Index: 166306 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.0286. Min Act: -0.0001

Data Index: 1029691 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1416425 (Python Code)

Max Activating Token Index: 281

Text #11

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9888. Min Act: -0.0001

Data Index: 843315 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9781. Min Act: -0.0001

Data Index: 1188894 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.0037. Min Act: -0.0001

Data Index: 1210318 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9084. Min Act: -0.0001

Data Index: 933928 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9844. Min Act: -0.0001

Data Index: 1522056 (Python Code)

Max Activating Token Index: 443

Text #16

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9023. Min Act: -0.0001

Data Index: 883344 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9504. Min Act: -0.0001

Data Index: 401589 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.0007. Min Act: -0.0001

Data Index: 1099074 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.5842. Min Range: -1.5842

Max Act: 0.9307. Min Act: -0.0001

Data Index: 138468 (C4 (Web Text))

Max Activating Token Index: 422