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

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

Neuron 291 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0842. Min Act: -0.1700

Data Index: 429149 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0369. Min Act: -0.1699

Data Index: 114471 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0369. Min Act: -0.1700

Data Index: 250636 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0369. Min Act: -0.1700

Data Index: 497310 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0527. Min Act: -0.1700

Data Index: 1321236 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0211. Min Act: -0.1700

Data Index: 585647 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0053. Min Act: -0.1700

Data Index: 440024 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0211. Min Act: -0.1700

Data Index: 1132394 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9895. Min Act: -0.1700

Data Index: 1246175 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0053. Min Act: -0.1700

Data Index: 874211 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0053. Min Act: -0.1700

Data Index: 965483 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0053. Min Act: -0.1700

Data Index: 116045 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0053. Min Act: -0.1700

Data Index: 1111432 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0053. Min Act: -0.1700

Data Index: 364318 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9895. Min Act: -0.1700

Data Index: 508295 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 3.0842. Min Range: -3.0842

Max Act: 3.0211. Min Act: -0.1700

Data Index: 931198 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9895. Min Act: -0.1700

Data Index: 710165 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9737. Min Act: -0.1700

Data Index: 719880 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9895. Min Act: -0.1700

Data Index: 815900 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 3.0842. Min Range: -3.0842

Max Act: 2.9578. Min Act: -0.1700

Data Index: 526915 (C4 (Web Text))

Max Activating Token Index: 378