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

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

Neuron 2045 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.1101. Min Act: -0.1700

Data Index: 712010 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.1101. Min Act: -0.1700

Data Index: 526470 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0943. Min Act: -0.1700

Data Index: 130678 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0943. Min Act: -0.1700

Data Index: 406436 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0786. Min Act: -0.1700

Data Index: 488135 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0786. Min Act: -0.1700

Data Index: 202673 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0470. Min Act: -0.1700

Data Index: 1286127 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0312. Min Act: -0.1700

Data Index: 263752 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0312. Min Act: -0.1700

Data Index: 1095411 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0312. Min Act: -0.1700

Data Index: 885999 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0470. Min Act: -0.1700

Data Index: 411600 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0312. Min Act: -0.1700

Data Index: 538984 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0154. Min Act: -0.1700

Data Index: 519648 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0154. Min Act: -0.1700

Data Index: 233459 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0154. Min Act: -0.1700

Data Index: 136680 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9996. Min Act: -0.1700

Data Index: 150655 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9996. Min Act: -0.1700

Data Index: 1290935 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9996. Min Act: -0.1700

Data Index: 1299028 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.1101. Min Range: -3.1101

Max Act: 3.0312. Min Act: -0.1700

Data Index: 757853 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 3.1101. Min Range: -3.1101

Max Act: 2.9838. Min Act: -0.1700

Data Index: 517977 (C4 (Web Text))

Max Activating Token Index: 967