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

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

Neuron 1289 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.4029. Min Act: -0.1700

Data Index: 957376 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.3401. Min Act: -0.1700

Data Index: 1241237 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.3244. Min Act: -0.1698

Data Index: 679184 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.3087. Min Act: -0.1700

Data Index: 307374 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.2459. Min Act: -0.1700

Data Index: 541979 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.2144. Min Act: -0.1700

Data Index: 1288964 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1987. Min Act: -0.1700

Data Index: 222763 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1987. Min Act: -0.1700

Data Index: 808565 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1830. Min Act: -0.1700

Data Index: 1171931 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1830. Min Act: -0.1700

Data Index: 438144 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1672. Min Act: -0.1700

Data Index: 556958 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1672. Min Act: -0.1700

Data Index: 729085 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1515. Min Act: -0.1700

Data Index: 1047791 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1357. Min Act: -0.1700

Data Index: 226173 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1515. Min Act: -0.1700

Data Index: 738182 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1357. Min Act: -0.1700

Data Index: 1064929 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1357. Min Act: -0.1700

Data Index: 311143 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1042. Min Act: -0.1673

Data Index: 1296360 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.1200. Min Act: -0.1700

Data Index: 371376 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 3.4029. Min Range: -3.4029

Max Act: 3.0884. Min Act: -0.1700

Data Index: 1317275 (C4 (Web Text))

Max Activating Token Index: 602