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

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

Neuron 4651 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.5092. Min Act: -0.0000

Data Index: 749679 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.2901. Min Act: -0.0000

Data Index: 1201489 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.4438. Min Act: -0.0000

Data Index: 699199 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.7463. Min Act: -0.0000

Data Index: 93955 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8602. Min Act: -0.0000

Data Index: 1137206 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.0879. Min Act: -0.0000

Data Index: 2402 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.0882. Min Act: -0.0000

Data Index: 1182582 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.0341. Min Act: -0.0000

Data Index: 670619 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.0095. Min Act: -0.0000

Data Index: 998417 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.1614. Min Act: -0.0000

Data Index: 847120 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.9384. Min Act: -0.0000

Data Index: 650525 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.9089. Min Act: -0.0000

Data Index: 750665 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8831. Min Act: -0.0000

Data Index: 91568 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8784. Min Act: -0.0000

Data Index: 385810 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8755. Min Act: -0.0000

Data Index: 24236 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 4.7463. Min Range: -4.7463

Max Act: 4.0405. Min Act: -0.0000

Data Index: 1107016 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8281. Min Act: -0.0000

Data Index: 643869 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8698. Min Act: -0.0000

Data Index: 1241453 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8488. Min Act: -0.0000

Data Index: 15949 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 4.7463. Min Range: -4.7463

Max Act: 3.8395. Min Act: -0.0000

Data Index: 1174998 (C4 (Web Text))

Max Activating Token Index: 260