Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1565 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.7697. Min Act: -0.1699

Data Index: 1310634 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.6135. Min Act: -0.1700

Data Index: 274894 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.6135. Min Act: -0.1700

Data Index: 925036 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.4572. Min Act: -0.1700

Data Index: 1099913 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.4572. Min Act: -0.1699

Data Index: 1234124 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.4260. Min Act: -0.1699

Data Index: 948149 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3947. Min Act: -0.1700

Data Index: 670417 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3322. Min Act: -0.1700

Data Index: 714861 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3947. Min Act: -0.1700

Data Index: 397217 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3322. Min Act: -0.1700

Data Index: 100606 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3010. Min Act: -0.1700

Data Index: 211814 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.2697. Min Act: -0.1700

Data Index: 1326412 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3947. Min Act: -0.1699

Data Index: 547183 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3322. Min Act: -0.1700

Data Index: 88241 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3322. Min Act: -0.1700

Data Index: 1106994 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.3010. Min Act: -0.1700

Data Index: 29552 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.2697. Min Act: -0.1700

Data Index: 62783 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.2072. Min Act: -0.1700

Data Index: 898389 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.2697. Min Act: -0.1700

Data Index: 232275 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 5.7697. Min Range: -5.7697

Max Act: 5.2385. Min Act: -0.1700

Data Index: 767478 (C4 (Web Text))

Max Activating Token Index: 418