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

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

Neuron 534 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 858989 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 146396 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 935289 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 927701 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 947993 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 745958 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 277014 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 667177 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.7258. Min Act: -0.1700

Data Index: 364360 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6945. Min Act: -0.1700

Data Index: 823002 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6945. Min Act: -0.1700

Data Index: 247519 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6945. Min Act: -0.1700

Data Index: 84546 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6475. Min Act: -0.1700

Data Index: 112973 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6319. Min Act: -0.1700

Data Index: 484363 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6319. Min Act: -0.1700

Data Index: 1321805 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6475. Min Act: -0.1700

Data Index: 30003 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6319. Min Act: -0.1700

Data Index: 438620 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6319. Min Act: -0.1700

Data Index: 770352 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6475. Min Act: -0.1700

Data Index: 760027 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 3.7258. Min Range: -3.7258

Max Act: 3.6162. Min Act: -0.1700

Data Index: 18987 (C4 (Web Text))

Max Activating Token Index: 350