Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1402 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.7708. Min Act: -0.1700

Data Index: 148172 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.7743. Min Act: -0.1700

Data Index: 1545730 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.7497. Min Act: -0.1700

Data Index: 202410 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.7514. Min Act: -0.1700

Data Index: 543119 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.7247. Min Act: -0.1700

Data Index: 94866 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6834. Min Act: -0.1700

Data Index: 751288 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6866. Min Act: -0.1700

Data Index: 1437504 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6889. Min Act: -0.1700

Data Index: 252939 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6669. Min Act: -0.1700

Data Index: 530784 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6363. Min Act: -0.1700

Data Index: 56630 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6622. Min Act: -0.1700

Data Index: 408723 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6635. Min Act: -0.1700

Data Index: 757097 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6507. Min Act: -0.1700

Data Index: 1293372 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6485. Min Act: -0.1700

Data Index: 1273786 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6369. Min Act: -0.1700

Data Index: 757971 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6450. Min Act: -0.1700

Data Index: 769975 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6254. Min Act: -0.1700

Data Index: 1476746 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6085. Min Act: -0.1700

Data Index: 686828 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6053. Min Act: -0.1700

Data Index: 1238312 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5973. Min Act: -0.1700

Data Index: 1473664 (Python Code)

Max Activating Token Index: 60