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

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

Neuron 1692 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: 3.2048. Min Range: -3.2048

Max Act: 3.2048. Min Act: -0.1700

Data Index: 1177704 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 3.2048. Min Range: -3.2048

Max Act: 3.1261. Min Act: -0.1700

Data Index: 924202 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 3.2048. Min Range: -3.2048

Max Act: 3.0630. Min Act: -0.1700

Data Index: 668886 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.2048. Min Range: -3.2048

Max Act: 3.0473. Min Act: -0.1700

Data Index: 443602 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.2048. Min Range: -3.2048

Max Act: 3.0473. Min Act: -0.1700

Data Index: 649325 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.2048. Min Range: -3.2048

Max Act: 3.0157. Min Act: -0.1700

Data Index: 789026 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 3.2048. Min Range: -3.2048

Max Act: 3.0157. Min Act: -0.1700

Data Index: 469325 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 3.2048. Min Range: -3.2048

Max Act: 3.0157. Min Act: -0.1700

Data Index: 112938 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9999. Min Act: -0.1700

Data Index: 165034 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9999. Min Act: -0.1700

Data Index: 1306901 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9524. Min Act: -0.1700

Data Index: 635388 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9524. Min Act: -0.1700

Data Index: 623590 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9524. Min Act: -0.1700

Data Index: 966205 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9366. Min Act: -0.1700

Data Index: 26092 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9366. Min Act: -0.1700

Data Index: 638185 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9207. Min Act: -0.1700

Data Index: 651931 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9207. Min Act: -0.1700

Data Index: 154479 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.9207. Min Act: -0.1700

Data Index: 611865 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.8731. Min Act: -0.1700

Data Index: 104543 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 3.2048. Min Range: -3.2048

Max Act: 2.8890. Min Act: -0.1700

Data Index: 1225260 (C4 (Web Text))

Max Activating Token Index: 761