Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1375 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1213. Min Range: -3.1213

Max Act: 3.1213. Min Act: -0.1700

Data Index: 1470027 (Python Code)

Max Activating Token Index: 779

Text #1

Max Range: 3.1213. Min Range: -3.1213

Max Act: 3.0583. Min Act: -0.1700

Data Index: 1356673 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 3.1213. Min Range: -3.1213

Max Act: 3.0267. Min Act: -0.1700

Data Index: 109484 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 3.1213. Min Range: -3.1213

Max Act: 3.0267. Min Act: -0.1700

Data Index: 703468 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9951. Min Act: -0.1700

Data Index: 726215 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9792. Min Act: -0.1700

Data Index: 1193257 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9792. Min Act: -0.1700

Data Index: 41960 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9634. Min Act: -0.1700

Data Index: 922278 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9634. Min Act: -0.1700

Data Index: 952343 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9792. Min Act: -0.1700

Data Index: 555562 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9476. Min Act: -0.1700

Data Index: 553085 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9476. Min Act: -0.1700

Data Index: 489676 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9318. Min Act: -0.1700

Data Index: 576461 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9318. Min Act: -0.1700

Data Index: 1089019 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9318. Min Act: -0.1700

Data Index: 916861 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9318. Min Act: -0.1700

Data Index: 306781 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9634. Min Act: -0.1700

Data Index: 1283131 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9159. Min Act: -0.1700

Data Index: 126913 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9159. Min Act: -0.1700

Data Index: 267527 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 3.1213. Min Range: -3.1213

Max Act: 2.9318. Min Act: -0.1700

Data Index: 407452 (C4 (Web Text))

Max Activating Token Index: 1008