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

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

Neuron 670 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: 0.4904. Min Range: -0.4904

Max Act: 0.4904. Min Act: -0.0000

Data Index: 688104 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4690. Min Act: -0.0000

Data Index: 78723 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4647. Min Act: -0.0000

Data Index: 325790 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4761. Min Act: -0.0000

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.4081. Min Act: -0.0000

Data Index: 133855 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3971. Min Act: -0.0000

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1096144 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3644. Min Act: -0.0000

Data Index: 852509 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1310325 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3694. Min Act: -0.0000

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3652. Min Act: -0.0000

Data Index: 668536 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1353494 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3356. Min Act: -0.0000

Data Index: 218870 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3181. Min Act: -0.0000

Data Index: 481556 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3148. Min Act: -0.0000

Data Index: 97881 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3508. Min Act: -0.0000

Data Index: 995316 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3108. Min Act: -0.0000

Data Index: 759181 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.2964. Min Act: -0.0000

Data Index: 459916 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1577096 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 0.4904. Min Range: -0.4904

Max Act: 0.2945. Min Act: -0.0000

Data Index: 854019 (C4 (Web Text))

Max Activating Token Index: 981