Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 355 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.3079. Min Act: -0.1700

Data Index: 500772 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.2454. Min Act: -0.1700

Data Index: 83395 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.1672. Min Act: -0.1700

Data Index: 1107388 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.1360. Min Act: -0.1700

Data Index: 410181 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.0891. Min Act: -0.1700

Data Index: 633912 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.0891. Min Act: -0.1700

Data Index: 532257 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.0735. Min Act: -0.1700

Data Index: 672903 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.0578. Min Act: -0.1700

Data Index: 1283749 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.0422. Min Act: -0.1700

Data Index: 690719 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.0266. Min Act: -0.1700

Data Index: 1219167 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 4.3079. Min Range: -4.3079

Max Act: 4.0422. Min Act: -0.1700

Data Index: 127505 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9797. Min Act: -0.1700

Data Index: 823536 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9484. Min Act: -0.1700

Data Index: 527764 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9953. Min Act: -0.1700

Data Index: 1087444 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9484. Min Act: -0.1700

Data Index: 83072 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9484. Min Act: -0.1700

Data Index: 520186 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9640. Min Act: -0.1700

Data Index: 1189428 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9640. Min Act: -0.1700

Data Index: 1225198 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9328. Min Act: -0.1699

Data Index: 127110 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 4.3079. Min Range: -4.3079

Max Act: 3.9171. Min Act: -0.1700

Data Index: 1224422 (C4 (Web Text))

Max Activating Token Index: 669