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

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

Neuron 1308 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: 3.7153. Min Range: -3.7153

Max Act: 3.7153. Min Act: -0.1700

Data Index: 173891 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.6527. Min Act: -0.1700

Data Index: 191955 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5901. Min Act: -0.1700

Data Index: 508887 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5901. Min Act: -0.1700

Data Index: 433941 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.6058. Min Act: -0.1700

Data Index: 1252838 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5745. Min Act: -0.1700

Data Index: 78438 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5431. Min Act: -0.1700

Data Index: 382215 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5588. Min Act: -0.1700

Data Index: 400335 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5275. Min Act: -0.1700

Data Index: 231837 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5275. Min Act: -0.1700

Data Index: 1012397 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5431. Min Act: -0.1700

Data Index: 389215 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5431. Min Act: -0.1700

Data Index: 1114077 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.4961. Min Act: -0.1700

Data Index: 712211 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5275. Min Act: -0.1700

Data Index: 252391 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.4805. Min Act: -0.1700

Data Index: 729455 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.4961. Min Act: -0.1700

Data Index: 1230656 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.4805. Min Act: -0.1700

Data Index: 717551 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.5431. Min Act: -0.1700

Data Index: 265122 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.4805. Min Act: -0.1700

Data Index: 23367 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 3.7153. Min Range: -3.7153

Max Act: 3.4334. Min Act: -0.1700

Data Index: 337280 (C4 (Web Text))

Max Activating Token Index: 387