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

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

Neuron 1367 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: 3.3150. Min Range: -3.3150

Max Act: 3.3150. Min Act: -0.1700

Data Index: 1159081 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2865. Min Act: -0.1700

Data Index: 767026 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2812. Min Act: -0.1700

Data Index: 505132 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2503. Min Act: -0.1700

Data Index: 660101 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1201314 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2323. Min Act: -0.1700

Data Index: 75165 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2407. Min Act: -0.1700

Data Index: 1298846 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.1727. Min Act: -0.1700

Data Index: 1495385 (Python Code)

Max Activating Token Index: 750

Text #8

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2258. Min Act: -0.1700

Data Index: 483460 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.1839. Min Act: -0.1700

Data Index: 171827 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2205. Min Act: -0.1700

Data Index: 780795 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2235. Min Act: -0.1700

Data Index: 13346 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2088. Min Act: -0.1700

Data Index: 1272303 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2004. Min Act: -0.1700

Data Index: 609130 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.1925. Min Act: -0.1700

Data Index: 1152713 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2135. Min Act: -0.1700

Data Index: 334490 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2251. Min Act: -0.1700

Data Index: 1304871 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1459743 (Python Code)

Max Activating Token Index: 388

Text #18

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.1802. Min Act: -0.1700

Data Index: 1533422 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 3.3150. Min Range: -3.3150

Max Act: 3.1664. Min Act: -0.1700

Data Index: 1876 (C4 (Web Text))

Max Activating Token Index: 125