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

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

Neuron 823 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: 3.7441. Min Range: -3.7441

Max Act: 3.7441. Min Act: -0.1700

Data Index: 1169313 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5876. Min Act: -0.1700

Data Index: 613975 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.4623. Min Act: -0.1700

Data Index: 587195 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3368. Min Act: -0.1700

Data Index: 1087532 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3995. Min Act: -0.1700

Data Index: 238438 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3682. Min Act: -0.1700

Data Index: 1166825 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3368. Min Act: -0.1700

Data Index: 143390 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3368. Min Act: -0.1700

Data Index: 13390 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3054. Min Act: -0.1700

Data Index: 735653 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2740. Min Act: -0.1700

Data Index: 636025 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2740. Min Act: -0.1700

Data Index: 299420 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3054. Min Act: -0.1700

Data Index: 482679 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1136751 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3054. Min Act: -0.1700

Data Index: 251761 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3054. Min Act: -0.1700

Data Index: 893615 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3368. Min Act: -0.1700

Data Index: 1323451 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2740. Min Act: -0.1700

Data Index: 418508 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.2425. Min Act: -0.1700

Data Index: 726506 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.3054. Min Act: -0.1700

Data Index: 421944 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.1796. Min Act: -0.1700

Data Index: 839680 (C4 (Web Text))

Max Activating Token Index: 736