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

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

Neuron 135 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: 5.8068. Min Range: -5.8068

Max Act: 5.8068. Min Act: -0.1699

Data Index: 624368 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.7443. Min Act: -0.1700

Data Index: 1170366 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.5880. Min Act: -0.1700

Data Index: 100223 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.5568. Min Act: -0.1700

Data Index: 1160336 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.5568. Min Act: -0.1700

Data Index: 1182049 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.5568. Min Act: -0.1700

Data Index: 471234 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4943. Min Act: -0.1700

Data Index: 996022 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.5255. Min Act: -0.1700

Data Index: 411132 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4630. Min Act: -0.1699

Data Index: 1352274 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4943. Min Act: -0.1700

Data Index: 323579 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4630. Min Act: -0.1700

Data Index: 605990 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4943. Min Act: -0.1700

Data Index: 75657 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4630. Min Act: -0.1700

Data Index: 328329 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4943. Min Act: -0.1700

Data Index: 188010 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4318. Min Act: -0.1700

Data Index: 9543 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4318. Min Act: -0.1700

Data Index: 249861 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4630. Min Act: -0.1700

Data Index: 367489 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4318. Min Act: -0.1700

Data Index: 324866 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4318. Min Act: -0.1700

Data Index: 95695 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 5.8068. Min Range: -5.8068

Max Act: 5.4005. Min Act: -0.1700

Data Index: 126283 (C4 (Web Text))

Max Activating Token Index: 492