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

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

Neuron 1235 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.3402. Min Act: -0.1700

Data Index: 58268 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.4340. Min Act: -0.1700

Data Index: 447901 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.3715. Min Act: -0.1700

Data Index: 1078374 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.3402. Min Act: -0.1700

Data Index: 593079 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.3402. Min Act: -0.1700

Data Index: 223565 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2777. Min Act: -0.1700

Data Index: 760996 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2465. Min Act: -0.1700

Data Index: 1163248 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2152. Min Act: -0.1700

Data Index: 34788 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2152. Min Act: -0.1700

Data Index: 890015 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2152. Min Act: -0.1700

Data Index: 765975 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2465. Min Act: -0.1700

Data Index: 879200 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2152. Min Act: -0.1700

Data Index: 993773 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1840. Min Act: -0.1700

Data Index: 228053 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.2152. Min Act: -0.1700

Data Index: 1165382 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1527. Min Act: -0.1700

Data Index: 967658 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1840. Min Act: -0.1700

Data Index: 97390 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.1215. Min Act: -0.1700

Data Index: 381784 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.0902. Min Act: -0.1700

Data Index: 864653 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.0902. Min Act: -0.1700

Data Index: 929494 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 5.4340. Min Range: -5.4340

Max Act: 5.0902. Min Act: -0.1700

Data Index: 615120 (C4 (Web Text))

Max Activating Token Index: 885