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

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

Neuron 1094 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: 5.0987. Min Range: -5.0987

Max Act: 4.9424. Min Act: -0.1700

Data Index: 779752 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 5.0987. Min Range: -5.0987

Max Act: 5.0987. Min Act: -0.1700

Data Index: 11202 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 5.0987. Min Range: -5.0987

Max Act: 5.0049. Min Act: -0.1700

Data Index: 153805 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.9737. Min Act: -0.1700

Data Index: 1316743 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.8487. Min Act: -0.1700

Data Index: 690459 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.8487. Min Act: -0.1700

Data Index: 632686 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.9112. Min Act: -0.1700

Data Index: 19101 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.7549. Min Act: -0.1700

Data Index: 779350 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.9112. Min Act: -0.1700

Data Index: 931579 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.7862. Min Act: -0.1700

Data Index: 1191766 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.8174. Min Act: -0.1700

Data Index: 264803 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.8487. Min Act: -0.1700

Data Index: 334240 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.8174. Min Act: -0.1700

Data Index: 647568 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.7549. Min Act: -0.1700

Data Index: 1097214 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.7862. Min Act: -0.1700

Data Index: 646565 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.7862. Min Act: -0.1700

Data Index: 173056 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.7862. Min Act: -0.1700

Data Index: 1209199 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.7549. Min Act: -0.1700

Data Index: 154067 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.6924. Min Act: -0.1700

Data Index: 673504 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 5.0987. Min Range: -5.0987

Max Act: 4.6612. Min Act: -0.1700

Data Index: 502174 (C4 (Web Text))

Max Activating Token Index: 968