Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2886 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1228705 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1637980 (Python Code)

Max Activating Token Index: 218

Text #2

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1618802 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1548447 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1496466 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3327. Min Act: -0.0000

Data Index: 766355 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1481363 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1468161 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1483616 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1436954 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1544370 (Python Code)

Max Activating Token Index: 488

Text #11

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1536359 (Python Code)

Max Activating Token Index: 607

Text #12

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1638594 (Python Code)

Max Activating Token Index: 808

Text #13

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1608948 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1572217 (Python Code)

Max Activating Token Index: 128

Text #15

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1301033 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1470146 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1389222 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1030804 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.4672. Min Range: -0.4672

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1471614 (Python Code)

Max Activating Token Index: 815