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

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

Neuron 981 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: 4.8965. Min Range: -4.8965

Max Act: 4.8965. Min Act: -0.1700

Data Index: 1067633 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.8034. Min Act: -0.1700

Data Index: 386584 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7886. Min Act: -0.1700

Data Index: 702433 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7636. Min Act: -0.1700

Data Index: 896715 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7854. Min Act: -0.1700

Data Index: 1315939 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7688. Min Act: -0.1700

Data Index: 855912 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7464. Min Act: -0.1700

Data Index: 262182 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7151. Min Act: -0.1700

Data Index: 977657 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7342. Min Act: -0.1700

Data Index: 391661 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7306. Min Act: -0.1700

Data Index: 1317827 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6519. Min Act: -0.1700

Data Index: 896515 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6845. Min Act: -0.1700

Data Index: 632830 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6840. Min Act: -0.1700

Data Index: 1052580 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.7499. Min Act: -0.1700

Data Index: 1245551 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6969. Min Act: -0.1700

Data Index: 231203 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6840. Min Act: -0.1700

Data Index: 932334 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6721. Min Act: -0.1700

Data Index: 423963 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6906. Min Act: -0.1700

Data Index: 382887 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6741. Min Act: -0.1700

Data Index: 101177 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 4.8965. Min Range: -4.8965

Max Act: 4.6461. Min Act: -0.1700

Data Index: 897770 (C4 (Web Text))

Max Activating Token Index: 607