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

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

Neuron 48 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.6450. Min Act: -0.1700

Data Index: 619354 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.5198. Min Act: -0.1700

Data Index: 350303 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.5511. Min Act: -0.1700

Data Index: 793284 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4884. Min Act: -0.1700

Data Index: 208020 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4884. Min Act: -0.1700

Data Index: 605201 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.5198. Min Act: -0.1700

Data Index: 242770 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4884. Min Act: -0.1700

Data Index: 88286 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4884. Min Act: -0.1700

Data Index: 1298843 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4884. Min Act: -0.1700

Data Index: 825896 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4571. Min Act: -0.1700

Data Index: 691172 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.3944. Min Act: -0.1700

Data Index: 904972 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4571. Min Act: -0.1700

Data Index: 331004 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4257. Min Act: -0.1700

Data Index: 1349261 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.3944. Min Act: -0.1700

Data Index: 644501 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4257. Min Act: -0.1700

Data Index: 464750 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.4257. Min Act: -0.1700

Data Index: 38905 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.3944. Min Act: -0.1700

Data Index: 290596 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.3630. Min Act: -0.1700

Data Index: 780213 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.3944. Min Act: -0.1700

Data Index: 380667 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 3.6450. Min Range: -3.6450

Max Act: 3.3944. Min Act: -0.1700

Data Index: 1098295 (C4 (Web Text))

Max Activating Token Index: 480