Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2215 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4923. Min Act: -0.0001

Data Index: 1188357 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.7293. Min Act: -0.0001

Data Index: 1321091 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.7236. Min Act: -0.0001

Data Index: 1135459 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.6166. Min Act: -0.0001

Data Index: 644084 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.6725. Min Act: -0.0001

Data Index: 377805 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.5084. Min Act: -0.0001

Data Index: 616862 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.5397. Min Act: -0.0001

Data Index: 823731 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.5826. Min Act: -0.0001

Data Index: 495444 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4819. Min Act: -0.0001

Data Index: 1070757 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4810. Min Act: -0.0001

Data Index: 1131497 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4803. Min Act: -0.0001

Data Index: 1256953 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4347. Min Act: -0.0001

Data Index: 770299 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.5481. Min Act: -0.0001

Data Index: 63569 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.3682. Min Act: -0.0001

Data Index: 1251026 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4330. Min Act: -0.0001

Data Index: 710654 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.3402. Min Act: -0.0001

Data Index: 1160149 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.4333. Min Act: -0.0001

Data Index: 474522 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.3335. Min Act: -0.0001

Data Index: 665072 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.3757. Min Act: -0.0001

Data Index: 1352071 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.7293. Min Range: -1.7293

Max Act: 1.3267. Min Act: -0.0001

Data Index: 164586 (C4 (Web Text))

Max Activating Token Index: 391