Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 426 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.4409. Min Act: -0.1700

Data Index: 487476 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.4438. Min Act: -0.1700

Data Index: 524075 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.4378. Min Act: -0.1700

Data Index: 856688 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.3446. Min Act: -0.1700

Data Index: 1300744 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.3399. Min Act: -0.1700

Data Index: 637970 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.2866. Min Act: -0.1700

Data Index: 45831 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.2480. Min Act: -0.1700

Data Index: 1163021 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.2352. Min Act: -0.1700

Data Index: 362495 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.1988. Min Act: -0.1700

Data Index: 202423 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.1803. Min Act: -0.1700

Data Index: 510346 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.1577. Min Act: -0.1700

Data Index: 461376 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.1238. Min Act: -0.1700

Data Index: 356537 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0830. Min Act: -0.1700

Data Index: 12622 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0891. Min Act: -0.1700

Data Index: 499686 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0574. Min Act: -0.1700

Data Index: 1094548 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0801. Min Act: -0.1700

Data Index: 902919 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0725. Min Act: -0.1700

Data Index: 503057 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0610. Min Act: -0.1700

Data Index: 898220 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0477. Min Act: -0.1700

Data Index: 1233632 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 4.4438. Min Range: -4.4438

Max Act: 4.0383. Min Act: -0.1700

Data Index: 607603 (C4 (Web Text))

Max Activating Token Index: 539