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

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

Neuron 4170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3732. Min Act: -0.0000

Data Index: 1495356 (Python Code)

Max Activating Token Index: 448

Text #1

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3164. Min Act: -0.0000

Data Index: 993129 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1251510 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2920. Min Act: -0.0000

Data Index: 96353 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1446375 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1048601 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2472. Min Act: -0.0000

Data Index: 999090 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1575547 (Python Code)

Max Activating Token Index: 360

Text #8

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1536463 (Python Code)

Max Activating Token Index: 267

Text #9

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2403. Min Act: -0.0000

Data Index: 563345 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2728. Min Act: -0.0000

Data Index: 698715 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2489. Min Act: -0.0000

Data Index: 468528 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2377. Min Act: -0.0000

Data Index: 139138 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2463. Min Act: -0.0000

Data Index: 800216 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2460. Min Act: -0.0000

Data Index: 1623039 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2315. Min Act: -0.0000

Data Index: 1651872 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1116238 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1115354 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2203. Min Act: -0.0000

Data Index: 195328 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1601258 (Python Code)

Max Activating Token Index: 690