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

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

Neuron 4961 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1104106 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.3293. Min Act: -0.0000

Data Index: 907321 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2780. Min Act: -0.0000

Data Index: 523095 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2913. Min Act: -0.0000

Data Index: 991025 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1153175 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2420. Min Act: -0.0000

Data Index: 996022 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1016881 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2420. Min Act: -0.0000

Data Index: 916931 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2475. Min Act: -0.0000

Data Index: 791247 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2287. Min Act: -0.0000

Data Index: 696106 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2506. Min Act: -0.0000

Data Index: 564433 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2485. Min Act: -0.0000

Data Index: 463256 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2224. Min Act: -0.0000

Data Index: 310556 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1352645 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2281. Min Act: -0.0000

Data Index: 669099 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2329. Min Act: -0.0000

Data Index: 462714 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1082849 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1202411 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1046828 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.3293. Min Range: -0.3293

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1074825 (C4 (Web Text))

Max Activating Token Index: 511