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

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

Neuron 1073 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.4803. Min Act: -0.1700

Data Index: 979656 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1492948 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3862. Min Act: -0.1700

Data Index: 1385260 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3862. Min Act: -0.1700

Data Index: 1406314 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.4176. Min Act: -0.1700

Data Index: 1564056 (Python Code)

Max Activating Token Index: 101

Text #5

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.4019. Min Act: -0.1700

Data Index: 268351 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3705. Min Act: -0.1700

Data Index: 694106 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3391. Min Act: -0.1700

Data Index: 1656955 (Python Code)

Max Activating Token Index: 523

Text #8

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3234. Min Act: -0.1700

Data Index: 1454979 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3548. Min Act: -0.1700

Data Index: 1361665 (Python Code)

Max Activating Token Index: 942

Text #10

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3548. Min Act: -0.1700

Data Index: 1641288 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3234. Min Act: -0.1700

Data Index: 1387806 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3391. Min Act: -0.1700

Data Index: 1519316 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3391. Min Act: -0.1700

Data Index: 1434545 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3391. Min Act: -0.1700

Data Index: 1417389 (Python Code)

Max Activating Token Index: 410

Text #15

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3077. Min Act: -0.1700

Data Index: 1634027 (Python Code)

Max Activating Token Index: 922

Text #16

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2920. Min Act: -0.1700

Data Index: 1561563 (Python Code)

Max Activating Token Index: 424

Text #17

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3234. Min Act: -0.1700

Data Index: 1452184 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.3234. Min Act: -0.1700

Data Index: 1411104 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 3.4803. Min Range: -3.4803

Max Act: 3.2920. Min Act: -0.1700

Data Index: 1582294 (Python Code)

Max Activating Token Index: 738