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

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

Neuron 633 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2002. Min Range: -3.2002

Max Act: 3.2002. Min Act: -0.0001

Data Index: 927167 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 3.2002. Min Range: -3.2002

Max Act: 3.0908. Min Act: -0.0001

Data Index: 122185 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.8629. Min Act: -0.0000

Data Index: 1221468 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.5936. Min Act: -0.0001

Data Index: 59740 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.6491. Min Act: -0.0001

Data Index: 899745 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.6274. Min Act: -0.0000

Data Index: 1084286 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.5942. Min Act: -0.0001

Data Index: 656680 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.5668. Min Act: -0.0000

Data Index: 849674 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.6901. Min Act: -0.0000

Data Index: 80752 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.6819. Min Act: -0.0001

Data Index: 373726 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.1860. Min Act: -0.0001

Data Index: 616140 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.5711. Min Act: -0.0001

Data Index: 921352 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.7337. Min Act: -0.0001

Data Index: 403860 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.3108. Min Act: -0.0001

Data Index: 477658 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.1780. Min Act: -0.0001

Data Index: 928778 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.1547. Min Act: -0.0001

Data Index: 506561 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.6050. Min Act: -0.0001

Data Index: 202822 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.4607. Min Act: -0.0001

Data Index: 713343 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.4128. Min Act: -0.0001

Data Index: 1347295 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 3.2002. Min Range: -3.2002

Max Act: 2.2904. Min Act: -0.0001

Data Index: 722725 (C4 (Web Text))

Max Activating Token Index: 707