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

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

Neuron 444 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: 3.7329. Min Range: -3.7329

Max Act: 3.7329. Min Act: -0.1700

Data Index: 1654388 (Python Code)

Max Activating Token Index: 768

Text #1

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.7185. Min Act: -0.1700

Data Index: 925740 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.6844. Min Act: -0.1700

Data Index: 1439840 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.6165. Min Act: -0.1700

Data Index: 1435809 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.6290. Min Act: -0.1700

Data Index: 283550 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5993. Min Act: -0.1700

Data Index: 1593748 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5771. Min Act: -0.1700

Data Index: 1366813 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5539. Min Act: -0.1700

Data Index: 59577 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5464. Min Act: -0.1700

Data Index: 1572438 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5389. Min Act: -0.1700

Data Index: 850625 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5289. Min Act: -0.1700

Data Index: 43893 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5222. Min Act: -0.1700

Data Index: 1488103 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5225. Min Act: -0.1700

Data Index: 646099 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5238. Min Act: -0.1700

Data Index: 1241221 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1514561 (Python Code)

Max Activating Token Index: 819

Text #15

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5113. Min Act: -0.1700

Data Index: 1582479 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5147. Min Act: -0.1700

Data Index: 509332 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5203. Min Act: -0.1700

Data Index: 382531 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5095. Min Act: -0.1700

Data Index: 1329947 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.7329. Min Range: -3.7329

Max Act: 3.5174. Min Act: -0.1700

Data Index: 296212 (C4 (Web Text))

Max Activating Token Index: 541