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

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

Neuron 3301 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: 0.8707. Min Range: -0.8707

Max Act: 0.8707. Min Act: -0.0000

Data Index: 973154 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6972. Min Act: -0.0000

Data Index: 849186 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6034. Min Act: -0.0000

Data Index: 800126 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5494. Min Act: -0.0000

Data Index: 83827 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5683. Min Act: -0.0000

Data Index: 207090 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1349362 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5558. Min Act: -0.0000

Data Index: 794818 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1047524 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5267. Min Act: -0.0000

Data Index: 342594 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5371. Min Act: -0.0000

Data Index: 545282 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5039. Min Act: -0.0000

Data Index: 770275 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1282935 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1076861 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1040658 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5049. Min Act: -0.0000

Data Index: 253518 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1088398 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4651. Min Act: -0.0000

Data Index: 331273 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4342. Min Act: -0.0000

Data Index: 523240 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1223291 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4505. Min Act: -0.0000

Data Index: 29457 (C4 (Web Text))

Max Activating Token Index: 370