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

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

Neuron 624 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: 5.0837. Min Range: -5.0837

Max Act: 5.0837. Min Act: -0.1700

Data Index: 432219 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 5.0837. Min Range: -5.0837

Max Act: 5.0837. Min Act: -0.1700

Data Index: 1652632 (Python Code)

Max Activating Token Index: 473

Text #2

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.9900. Min Act: -0.1700

Data Index: 505264 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.9587. Min Act: -0.1700

Data Index: 99388 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.9900. Min Act: -0.1700

Data Index: 721929 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8962. Min Act: -0.1700

Data Index: 187040 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.9587. Min Act: -0.1700

Data Index: 1319725 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8650. Min Act: -0.1700

Data Index: 504949 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8650. Min Act: -0.1700

Data Index: 528953 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8337. Min Act: -0.1700

Data Index: 1238185 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8650. Min Act: -0.1700

Data Index: 288209 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8337. Min Act: -0.1700

Data Index: 391958 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8025. Min Act: -0.1700

Data Index: 486256 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.8337. Min Act: -0.1700

Data Index: 223306 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.7712. Min Act: -0.1700

Data Index: 96154 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.7400. Min Act: -0.1700

Data Index: 946826 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.7712. Min Act: -0.1700

Data Index: 765474 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.7400. Min Act: -0.1700

Data Index: 1081454 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.6775. Min Act: -0.1700

Data Index: 8586 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 5.0837. Min Range: -5.0837

Max Act: 4.7400. Min Act: -0.1700

Data Index: 523654 (C4 (Web Text))

Max Activating Token Index: 925