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

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

Neuron 705 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.1657. Min Act: -0.1700

Data Index: 1029003 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.1657. Min Act: -0.1700

Data Index: 177423 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.1342. Min Act: -0.1700

Data Index: 676744 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.1027. Min Act: -0.1700

Data Index: 207804 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.1027. Min Act: -0.1700

Data Index: 894318 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0869. Min Act: -0.1700

Data Index: 65261 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0711. Min Act: -0.1700

Data Index: 1163120 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0711. Min Act: -0.1700

Data Index: 27979 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0553. Min Act: -0.1700

Data Index: 132290 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0711. Min Act: -0.1700

Data Index: 475408 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0396. Min Act: -0.1700

Data Index: 565771 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0553. Min Act: -0.1700

Data Index: 932658 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0080. Min Act: -0.1700

Data Index: 801292 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0238. Min Act: -0.1700

Data Index: 1147978 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 3.1657. Min Range: -3.1657

Max Act: 2.9921. Min Act: -0.1700

Data Index: 288361 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.1657. Min Range: -3.1657

Max Act: 3.0080. Min Act: -0.1700

Data Index: 1116004 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 3.1657. Min Range: -3.1657

Max Act: 2.9763. Min Act: -0.1700

Data Index: 1043807 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 3.1657. Min Range: -3.1657

Max Act: 2.9921. Min Act: -0.1700

Data Index: 576638 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 3.1657. Min Range: -3.1657

Max Act: 2.9605. Min Act: -0.1700

Data Index: 541023 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 3.1657. Min Range: -3.1657

Max Act: 2.9763. Min Act: -0.1700

Data Index: 799957 (C4 (Web Text))

Max Activating Token Index: 664