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

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

Neuron 703 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: 3.5514. Min Range: -3.5514

Max Act: 3.5514. Min Act: -0.1700

Data Index: 1408828 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3947. Min Act: -0.1700

Data Index: 738693 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3633. Min Act: -0.1700

Data Index: 444745 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3319. Min Act: -0.1700

Data Index: 684565 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3319. Min Act: -0.1700

Data Index: 1575196 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3633. Min Act: -0.1700

Data Index: 1354860 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 1056374 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3005. Min Act: -0.1700

Data Index: 1452914 (Python Code)

Max Activating Token Index: 349

Text #8

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 794182 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 1023300 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3005. Min Act: -0.1700

Data Index: 623483 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3005. Min Act: -0.1700

Data Index: 423221 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3005. Min Act: -0.1700

Data Index: 149102 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 833026 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 362338 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2377. Min Act: -0.1700

Data Index: 1104024 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.3005. Min Act: -0.1700

Data Index: 177468 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 96204 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 49879 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 3.5514. Min Range: -3.5514

Max Act: 3.2691. Min Act: -0.1700

Data Index: 429110 (C4 (Web Text))

Max Activating Token Index: 451