Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 3 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.0336. Min Range: -3.0336

Max Act: 3.0336. Min Act: -0.1700

Data Index: 1105798 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 3.0336. Min Range: -3.0336

Max Act: 3.0038. Min Act: -0.1700

Data Index: 334411 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9832. Min Act: -0.1700

Data Index: 254964 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9954. Min Act: -0.1700

Data Index: 661613 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9343. Min Act: -0.1700

Data Index: 250725 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9024. Min Act: -0.1700

Data Index: 812778 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9182. Min Act: -0.1700

Data Index: 852064 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9285. Min Act: -0.1700

Data Index: 953218 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9089. Min Act: -0.1700

Data Index: 1338686 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.9150. Min Act: -0.1700

Data Index: 611583 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8967. Min Act: -0.1700

Data Index: 721250 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8846. Min Act: -0.1700

Data Index: 1010283 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8821. Min Act: -0.1700

Data Index: 388337 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8645. Min Act: -0.1700

Data Index: 782589 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8782. Min Act: -0.1700

Data Index: 197210 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8716. Min Act: -0.1700

Data Index: 1213185 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8820. Min Act: -0.1700

Data Index: 297994 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8475. Min Act: -0.1700

Data Index: 300056 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8557. Min Act: -0.1700

Data Index: 509737 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 3.0336. Min Range: -3.0336

Max Act: 2.8552. Min Act: -0.1700

Data Index: 582064 (C4 (Web Text))

Max Activating Token Index: 460