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

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

Neuron 1133 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: 3.5543. Min Range: -3.5543

Max Act: 3.5425. Min Act: -0.1700

Data Index: 1042584 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.5543. Min Act: -0.1700

Data Index: 1173327 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.4135. Min Act: -0.1700

Data Index: 1047835 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.4127. Min Act: -0.1700

Data Index: 827029 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.4083. Min Act: -0.1700

Data Index: 826034 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.3708. Min Act: -0.1700

Data Index: 120333 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.3683. Min Act: -0.1700

Data Index: 509181 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.3363. Min Act: -0.1700

Data Index: 296290 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.3193. Min Act: -0.1700

Data Index: 340380 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.3153. Min Act: -0.1700

Data Index: 650610 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2659. Min Act: -0.1700

Data Index: 1076673 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2804. Min Act: -0.1700

Data Index: 98271 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2692. Min Act: -0.1700

Data Index: 842472 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2546. Min Act: -0.1700

Data Index: 468677 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2601. Min Act: -0.1700

Data Index: 930166 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2668. Min Act: -0.1700

Data Index: 664878 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2447. Min Act: -0.1700

Data Index: 259685 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2650. Min Act: -0.1700

Data Index: 407516 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2581. Min Act: -0.1700

Data Index: 1015415 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 3.5543. Min Range: -3.5543

Max Act: 3.2563. Min Act: -0.1700

Data Index: 836650 (C4 (Web Text))

Max Activating Token Index: 858