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

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

Neuron 1850 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: 4.2598. Min Range: -4.2598

Max Act: 4.2598. Min Act: -0.1684

Data Index: 217806 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 4.2598. Min Range: -4.2598

Max Act: 4.2019. Min Act: -0.1698

Data Index: 248908 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 4.2598. Min Range: -4.2598

Max Act: 4.1819. Min Act: -0.1700

Data Index: 481167 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 4.2598. Min Range: -4.2598

Max Act: 4.0778. Min Act: -0.1696

Data Index: 846505 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 4.2598. Min Range: -4.2598

Max Act: 4.0103. Min Act: -0.1632

Data Index: 888435 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.9356. Min Act: -0.1632

Data Index: 867702 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8956. Min Act: -0.1632

Data Index: 1004711 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8994. Min Act: -0.1632

Data Index: 926311 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8758. Min Act: -0.1632

Data Index: 551295 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8896. Min Act: -0.1700

Data Index: 314102 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8420. Min Act: -0.1700

Data Index: 891667 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8570. Min Act: -0.1699

Data Index: 938926 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8532. Min Act: -0.1700

Data Index: 926079 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8458. Min Act: -0.1700

Data Index: 1146976 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8345. Min Act: -0.1632

Data Index: 320260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8277. Min Act: -0.1684

Data Index: 558995 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8275. Min Act: -0.1632

Data Index: 376264 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8304. Min Act: -0.1700

Data Index: 1236515 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8410. Min Act: -0.1700

Data Index: 485361 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 4.2598. Min Range: -4.2598

Max Act: 3.8353. Min Act: -0.1695

Data Index: 846286 (C4 (Web Text))

Max Activating Token Index: 121