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

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

Neuron 971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5835. Min Act: -0.1700

Data Index: 979479 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5209. Min Act: -0.1700

Data Index: 481466 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5052. Min Act: -0.1700

Data Index: 1163099 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5365. Min Act: -0.1700

Data Index: 1241092 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4895. Min Act: -0.1700

Data Index: 840985 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5209. Min Act: -0.1700

Data Index: 488618 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5365. Min Act: -0.1700

Data Index: 689518 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5522. Min Act: -0.1700

Data Index: 1028567 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4895. Min Act: -0.1700

Data Index: 1145876 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4895. Min Act: -0.1700

Data Index: 74484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4582. Min Act: -0.1700

Data Index: 980075 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4895. Min Act: -0.1700

Data Index: 560941 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4895. Min Act: -0.1700

Data Index: 2892 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4582. Min Act: -0.1700

Data Index: 99621 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4582. Min Act: -0.1700

Data Index: 767053 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5052. Min Act: -0.1700

Data Index: 752716 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4582. Min Act: -0.1700

Data Index: 1069835 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4739. Min Act: -0.1700

Data Index: 174540 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.5209. Min Act: -0.1700

Data Index: 598920 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 3.5835. Min Range: -3.5835

Max Act: 3.4582. Min Act: -0.1700

Data Index: 429408 (C4 (Web Text))

Max Activating Token Index: 803