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

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

Neuron 4468 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.9259. Min Act: -0.0000

Data Index: 85651 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.5977. Min Act: -0.0000

Data Index: 735295 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4442. Min Act: -0.0000

Data Index: 574483 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.5803. Min Act: -0.0000

Data Index: 380546 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.5790. Min Act: -0.0000

Data Index: 185951 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4761. Min Act: -0.0000

Data Index: 877297 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.5120. Min Act: 0.0000

Data Index: 634593 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4525. Min Act: -0.0000

Data Index: 675188 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4935. Min Act: -0.0000

Data Index: 585069 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4561. Min Act: -0.0000

Data Index: 305037 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4210. Min Act: -0.0000

Data Index: 747291 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4269. Min Act: 0.0000

Data Index: 1293058 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1238496 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4463. Min Act: -0.0000

Data Index: 339120 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4514. Min Act: 0.0000

Data Index: 84972 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4392. Min Act: -0.0000

Data Index: 916912 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.3992. Min Act: -0.0000

Data Index: 920387 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4000. Min Act: -0.0000

Data Index: 565498 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4233. Min Act: -0.0000

Data Index: 931231 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.9259. Min Range: -0.9259

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1102684 (C4 (Web Text))

Max Activating Token Index: 597