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

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

Neuron 969 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: 5.1338. Min Range: -5.1338

Max Act: 5.1338. Min Act: -0.1700

Data Index: 290635 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9151. Min Act: -0.1700

Data Index: 612295 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7901. Min Act: -0.1700

Data Index: 230398 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.8213. Min Act: -0.1700

Data Index: 1175749 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.9151. Min Act: -0.1700

Data Index: 754738 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.8526. Min Act: -0.1700

Data Index: 64521 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7588. Min Act: -0.1700

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7901. Min Act: -0.1700

Data Index: 982051 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7901. Min Act: -0.1700

Data Index: 1064440 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7901. Min Act: -0.1700

Data Index: 1003887 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7901. Min Act: -0.1700

Data Index: 79421 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7901. Min Act: -0.1700

Data Index: 954595 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7901. Min Act: -0.1700

Data Index: 982616 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.6651. Min Act: -0.1700

Data Index: 764220 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.6494. Min Act: -0.1700

Data Index: 1215198 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.7276. Min Act: -0.1700

Data Index: 702506 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.6963. Min Act: -0.1700

Data Index: 1285316 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.6963. Min Act: -0.1700

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.6651. Min Act: -0.1700

Data Index: 910435 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 5.1338. Min Range: -5.1338

Max Act: 4.6494. Min Act: -0.1700

Data Index: 49424 (C4 (Web Text))

Max Activating Token Index: 50