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

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

Neuron 719 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: 3.9397. Min Range: -3.9397

Max Act: 3.9397. Min Act: -0.1700

Data Index: 1128905 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8459. Min Act: -0.1700

Data Index: 747123 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7834. Min Act: -0.1700

Data Index: 370255 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8146. Min Act: -0.1700

Data Index: 294634 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7834. Min Act: -0.1700

Data Index: 319255 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8146. Min Act: -0.1700

Data Index: 187850 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6895. Min Act: -0.1700

Data Index: 1035901 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6582. Min Act: -0.1700

Data Index: 1022072 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6895. Min Act: -0.1700

Data Index: 674412 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6425. Min Act: -0.1700

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6269. Min Act: -0.1700

Data Index: 499187 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6112. Min Act: -0.1700

Data Index: 1091044 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6425. Min Act: -0.1700

Data Index: 465254 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1064470 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6112. Min Act: -0.1700

Data Index: 1134796 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7208. Min Act: -0.1700

Data Index: 742749 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.5956. Min Act: -0.1700

Data Index: 1144318 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6425. Min Act: -0.1700

Data Index: 235554 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6112. Min Act: -0.1700

Data Index: 304924 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.6112. Min Act: -0.1700

Data Index: 209709 (C4 (Web Text))

Max Activating Token Index: 1023