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

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

Neuron 2408 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1963. Min Range: -2.1963

Max Act: 2.1963. Min Act: -0.0000

Data Index: 737996 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.1963. Min Range: -2.1963

Max Act: 2.0306. Min Act: -0.0000

Data Index: 1336872 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.9138. Min Act: 0.0000

Data Index: 558329 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.8885. Min Act: -0.0000

Data Index: 510050 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.9905. Min Act: -0.0000

Data Index: 1091227 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.8463. Min Act: -0.0000

Data Index: 1251450 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.8411. Min Act: -0.0000

Data Index: 185400 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.8392. Min Act: -0.0000

Data Index: 996017 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.6643. Min Act: -0.0000

Data Index: 1319092 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.7438. Min Act: -0.0000

Data Index: 125796 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.6907. Min Act: -0.0000

Data Index: 782069 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.6543. Min Act: -0.0000

Data Index: 1331597 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.6778. Min Act: -0.0000

Data Index: 42124 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.4947. Min Act: -0.0000

Data Index: 506254 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1258317 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.4466. Min Act: -0.0000

Data Index: 492120 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1036061 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.5286. Min Act: -0.0000

Data Index: 285996 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.5293. Min Act: -0.0000

Data Index: 467647 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 2.1963. Min Range: -2.1963

Max Act: 1.5265. Min Act: -0.0000

Data Index: 126289 (C4 (Web Text))

Max Activating Token Index: 282