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

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

Neuron 597 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: 3.4248. Min Range: -3.4248

Max Act: 3.4248. Min Act: -0.1700

Data Index: 601845 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.3306. Min Act: -0.1700

Data Index: 1166833 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.3463. Min Act: -0.1700

Data Index: 1254032 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.2992. Min Act: -0.1700

Data Index: 1089540 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1051694 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.2364. Min Act: -0.1700

Data Index: 503388 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1892. Min Act: -0.1700

Data Index: 967110 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1892. Min Act: -0.1700

Data Index: 482544 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1577. Min Act: -0.1700

Data Index: 340922 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1419. Min Act: -0.1700

Data Index: 501592 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1419. Min Act: -0.1700

Data Index: 1128171 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1577. Min Act: -0.1700

Data Index: 184716 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1104. Min Act: -0.1700

Data Index: 874229 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1419. Min Act: -0.1700

Data Index: 1095940 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.0947. Min Act: -0.1700

Data Index: 577644 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.0947. Min Act: -0.1700

Data Index: 709598 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.1104. Min Act: -0.1700

Data Index: 276168 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.0947. Min Act: -0.1700

Data Index: 1051051 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.0789. Min Act: -0.1700

Data Index: 944050 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.4248. Min Range: -3.4248

Max Act: 3.0947. Min Act: -0.1700

Data Index: 554347 (C4 (Web Text))

Max Activating Token Index: 252