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

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

Neuron 1174 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.4413. Min Act: -0.1700

Data Index: 467142 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.4101. Min Act: -0.1700

Data Index: 1041457 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.3163. Min Act: -0.1700

Data Index: 572187 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.3163. Min Act: -0.1700

Data Index: 1046968 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.2538. Min Act: -0.1700

Data Index: 268265 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.2538. Min Act: -0.1700

Data Index: 388940 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.2226. Min Act: -0.1700

Data Index: 106639 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1601. Min Act: -0.1700

Data Index: 636694 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1913. Min Act: -0.1700

Data Index: 559362 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.2538. Min Act: -0.1700

Data Index: 1098164 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.2226. Min Act: -0.1700

Data Index: 287044 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1288. Min Act: -0.1700

Data Index: 720052 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1913. Min Act: -0.1700

Data Index: 869029 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1913. Min Act: -0.1700

Data Index: 901420 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1288. Min Act: -0.1700

Data Index: 959192 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1601. Min Act: -0.1700

Data Index: 353289 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1288. Min Act: -0.1700

Data Index: 1268181 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1601. Min Act: -0.1700

Data Index: 934145 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1601. Min Act: -0.1700

Data Index: 195748 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 5.4413. Min Range: -5.4413

Max Act: 5.1601. Min Act: -0.1700

Data Index: 829533 (C4 (Web Text))

Max Activating Token Index: 36