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

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

Neuron 592 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1164238 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.3159. Min Act: -0.1700

Data Index: 260072 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1902. Min Act: -0.1700

Data Index: 419393 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1902. Min Act: -0.1700

Data Index: 1327387 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1587. Min Act: -0.1700

Data Index: 1351029 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1902. Min Act: -0.1700

Data Index: 662378 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1272. Min Act: -0.1700

Data Index: 456962 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1272. Min Act: -0.1700

Data Index: 322063 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1272. Min Act: -0.1700

Data Index: 189033 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0799. Min Act: -0.1700

Data Index: 464720 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1272. Min Act: -0.1700

Data Index: 232419 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1272. Min Act: -0.1700

Data Index: 1129802 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.1114. Min Act: -0.1700

Data Index: 896589 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0957. Min Act: -0.1700

Data Index: 374247 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0641. Min Act: -0.1700

Data Index: 1135120 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0957. Min Act: -0.1700

Data Index: 981410 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0641. Min Act: -0.1700

Data Index: 921374 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0641. Min Act: -0.1700

Data Index: 16461 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0799. Min Act: -0.1700

Data Index: 302124 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 3.3787. Min Range: -3.3787

Max Act: 3.0957. Min Act: -0.1700

Data Index: 318628 (C4 (Web Text))

Max Activating Token Index: 779