Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 807 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0913. Min Range: -5.0913

Max Act: 5.0913. Min Act: -0.1700

Data Index: 1259733 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.2475. Min Act: -0.1700

Data Index: 1198970 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.2475. Min Act: -0.1700

Data Index: 529217 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.2787. Min Act: -0.1700

Data Index: 289962 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.2475. Min Act: -0.1700

Data Index: 582482 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1537. Min Act: -0.1700

Data Index: 1324891 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.2162. Min Act: -0.1700

Data Index: 863954 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1850. Min Act: -0.1700

Data Index: 661683 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1850. Min Act: -0.1700

Data Index: 1275941 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.2475. Min Act: -0.1700

Data Index: 1010939 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1850. Min Act: -0.1700

Data Index: 1234366 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1537. Min Act: -0.1700

Data Index: 1346204 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1850. Min Act: -0.1700

Data Index: 977439 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1224. Min Act: -0.1700

Data Index: 471957 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.1224. Min Act: -0.1700

Data Index: 905569 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.0599. Min Act: -0.1700

Data Index: 470140 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.0443. Min Act: -0.1700

Data Index: 42343 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.0287. Min Act: -0.1700

Data Index: 867383 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.0130. Min Act: -0.1700

Data Index: 1233001 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 5.0913. Min Range: -5.0913

Max Act: 4.0443. Min Act: -0.1700

Data Index: 944707 (C4 (Web Text))

Max Activating Token Index: 526