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

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

Neuron 1474 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: 5.3193. Min Range: -5.3193

Max Act: 5.3193. Min Act: -0.1700

Data Index: 216138 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1943. Min Act: -0.1700

Data Index: 351942 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1318. Min Act: -0.1700

Data Index: 374462 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1631. Min Act: -0.1700

Data Index: 939265 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.1006. Min Act: -0.1700

Data Index: 824907 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.0381. Min Act: -0.1700

Data Index: 405049 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 5.3193. Min Range: -5.3193

Max Act: 5.0068. Min Act: -0.1700

Data Index: 103975 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9756. Min Act: -0.1700

Data Index: 88105 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9756. Min Act: -0.1700

Data Index: 1025651 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 562620 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 1328713 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9443. Min Act: -0.1700

Data Index: 895567 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 287046 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 512107 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.9131. Min Act: -0.1700

Data Index: 1248297 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.8818. Min Act: -0.1700

Data Index: 437408 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.8818. Min Act: -0.1700

Data Index: 417274 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.8193. Min Act: -0.1700

Data Index: 135240 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.8506. Min Act: -0.1700

Data Index: 464240 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 5.3193. Min Range: -5.3193

Max Act: 4.8818. Min Act: -0.1700

Data Index: 371335 (C4 (Web Text))

Max Activating Token Index: 358