Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1814 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.7085. Min Act: -0.1700

Data Index: 1242872 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.6615. Min Act: -0.1700

Data Index: 358840 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.5519. Min Act: -0.1700

Data Index: 818518 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.5049. Min Act: -0.1700

Data Index: 116798 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.5206. Min Act: -0.1700

Data Index: 1341382 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4893. Min Act: -0.1700

Data Index: 1021101 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.5363. Min Act: -0.1700

Data Index: 198324 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4579. Min Act: -0.1700

Data Index: 1335577 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4893. Min Act: -0.1700

Data Index: 800359 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4579. Min Act: -0.1700

Data Index: 802656 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4266. Min Act: -0.1700

Data Index: 52740 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4266. Min Act: -0.1700

Data Index: 206008 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4109. Min Act: -0.1700

Data Index: 1357921 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4109. Min Act: -0.1700

Data Index: 1018084 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.3795. Min Act: -0.1700

Data Index: 9933 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.4109. Min Act: -0.1700

Data Index: 487804 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.3795. Min Act: -0.1700

Data Index: 1035358 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.3952. Min Act: -0.1700

Data Index: 637632 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.3638. Min Act: -0.1700

Data Index: 112353 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 3.7085. Min Range: -3.7085

Max Act: 3.3795. Min Act: -0.1700

Data Index: 292976 (C4 (Web Text))

Max Activating Token Index: 857