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

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

Neuron 1052 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: 4.5491. Min Range: -4.5491

Max Act: 4.5491. Min Act: -0.1700

Data Index: 700156 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.5083. Min Act: -0.1700

Data Index: 951604 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.4295. Min Act: -0.1700

Data Index: 455544 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.4442. Min Act: -0.1700

Data Index: 629908 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.4167. Min Act: -0.1700

Data Index: 604523 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3814. Min Act: -0.1700

Data Index: 1269635 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.4240. Min Act: -0.1700

Data Index: 1183553 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.4629. Min Act: -0.1700

Data Index: 537477 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.4268. Min Act: -0.1700

Data Index: 144707 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3921. Min Act: -0.1700

Data Index: 1035681 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3639. Min Act: -0.1700

Data Index: 508000 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3528. Min Act: -0.1700

Data Index: 354810 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3474. Min Act: -0.1700

Data Index: 289978 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3575. Min Act: -0.1700

Data Index: 1092292 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.4067. Min Act: -0.1700

Data Index: 707543 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3601. Min Act: -0.1700

Data Index: 746690 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3318. Min Act: -0.1700

Data Index: 794985 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3496. Min Act: -0.1700

Data Index: 229426 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3803. Min Act: -0.1700

Data Index: 1201321 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 4.5491. Min Range: -4.5491

Max Act: 4.3542. Min Act: -0.1700

Data Index: 674093 (C4 (Web Text))

Max Activating Token Index: 226