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

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

Neuron 1542 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.3833. Min Act: -0.1700

Data Index: 760103 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1301020 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1633. Min Act: -0.1700

Data Index: 661135 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1318. Min Act: -0.1700

Data Index: 312869 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1633. Min Act: -0.1700

Data Index: 1099004 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1633. Min Act: -0.1700

Data Index: 957593 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1633. Min Act: -0.1700

Data Index: 625890 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1318. Min Act: -0.1700

Data Index: 1152971 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1161. Min Act: -0.1700

Data Index: 128419 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1161. Min Act: -0.1700

Data Index: 552830 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1318. Min Act: -0.1700

Data Index: 1145322 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1633. Min Act: -0.1700

Data Index: 850802 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1318. Min Act: -0.1700

Data Index: 1076830 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1318. Min Act: -0.1700

Data Index: 659945 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1003. Min Act: -0.1700

Data Index: 647257 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1161. Min Act: -0.1700

Data Index: 1325725 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1003. Min Act: -0.1700

Data Index: 116737 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1003. Min Act: -0.1700

Data Index: 1217056 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.1003. Min Act: -0.1700

Data Index: 1283318 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 3.3833. Min Range: -3.3833

Max Act: 3.0845. Min Act: -0.1700

Data Index: 588966 (C4 (Web Text))

Max Activating Token Index: 499