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

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

Neuron 182 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.5697. Min Act: -0.1700

Data Index: 426148 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.3197. Min Act: -0.1700

Data Index: 401912 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.0697. Min Act: -0.1700

Data Index: 1143630 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.0072. Min Act: -0.1700

Data Index: 379248 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.0072. Min Act: -0.1700

Data Index: 67042 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.0385. Min Act: -0.1700

Data Index: 1218111 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.9760. Min Act: -0.1700

Data Index: 216701 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.0385. Min Act: -0.1700

Data Index: 316887 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 5.5697. Min Range: -5.5697

Max Act: 5.0072. Min Act: -0.1700

Data Index: 661672 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.9447. Min Act: -0.1700

Data Index: 511932 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.9447. Min Act: -0.1700

Data Index: 975025 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.8822. Min Act: -0.1700

Data Index: 556527 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.9135. Min Act: -0.1700

Data Index: 453022 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.8822. Min Act: -0.1700

Data Index: 139050 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.8822. Min Act: -0.1700

Data Index: 1061248 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.8510. Min Act: -0.1700

Data Index: 307766 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.8510. Min Act: -0.1700

Data Index: 327763 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.8822. Min Act: -0.1700

Data Index: 101276 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.8510. Min Act: -0.1700

Data Index: 449101 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 5.5697. Min Range: -5.5697

Max Act: 4.9447. Min Act: -0.1700

Data Index: 841547 (C4 (Web Text))

Max Activating Token Index: 348