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

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

Neuron 515 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.8128. Min Act: -0.1700

Data Index: 423335 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.8128. Min Act: -0.1700

Data Index: 411641 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.8128. Min Act: -0.1700

Data Index: 90702 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.7191. Min Act: -0.1700

Data Index: 373718 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.7191. Min Act: -0.1700

Data Index: 1030567 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.4691. Min Act: -0.1700

Data Index: 608811 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.4378. Min Act: -0.1700

Data Index: 1271704 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.3441. Min Act: -0.1700

Data Index: 1125052 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.3128. Min Act: -0.1700

Data Index: 1265038 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.2503. Min Act: -0.1700

Data Index: 542034 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.1253. Min Act: -0.1700

Data Index: 24244 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.1878. Min Act: -0.1700

Data Index: 469126 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.0316. Min Act: -0.1700

Data Index: 119700 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.1566. Min Act: -0.1700

Data Index: 516216 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.1253. Min Act: -0.1700

Data Index: 707121 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.1878. Min Act: -0.1700

Data Index: 1047474 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.0941. Min Act: -0.1700

Data Index: 255295 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.2816. Min Act: -0.1700

Data Index: 1257292 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.0941. Min Act: -0.1700

Data Index: 1035093 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 5.8128. Min Range: -5.8128

Max Act: 5.1566. Min Act: -0.1700

Data Index: 617034 (C4 (Web Text))

Max Activating Token Index: 874