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

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

Neuron 219 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: 3.9027. Min Range: -3.9027

Max Act: 3.9027. Min Act: -0.1700

Data Index: 986510 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.8088. Min Act: -0.1700

Data Index: 1025445 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.7619. Min Act: -0.1700

Data Index: 793772 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.7619. Min Act: -0.1700

Data Index: 423106 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.7463. Min Act: -0.1700

Data Index: 1111186 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.7306. Min Act: -0.1700

Data Index: 309066 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.7150. Min Act: -0.1700

Data Index: 485420 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6837. Min Act: -0.1700

Data Index: 434896 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6680. Min Act: -0.1700

Data Index: 39723 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6680. Min Act: -0.1700

Data Index: 1310557 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6367. Min Act: -0.1700

Data Index: 440431 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6367. Min Act: -0.1700

Data Index: 1183914 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6211. Min Act: -0.1700

Data Index: 1168259 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6211. Min Act: -0.1700

Data Index: 790532 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6054. Min Act: -0.1700

Data Index: 752851 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6367. Min Act: -0.1700

Data Index: 841948 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6211. Min Act: -0.1700

Data Index: 34116 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6054. Min Act: -0.1700

Data Index: 771079 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6054. Min Act: -0.1700

Data Index: 145905 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 3.9027. Min Range: -3.9027

Max Act: 3.6211. Min Act: -0.1700

Data Index: 229249 (C4 (Web Text))

Max Activating Token Index: 580