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

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

Neuron 1065 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: 2.9943. Min Range: -2.9943

Max Act: 2.9943. Min Act: -0.1700

Data Index: 110583 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.8391. Min Act: -0.1700

Data Index: 697158 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7893. Min Act: -0.1700

Data Index: 1605378 (Python Code)

Max Activating Token Index: 454

Text #3

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7965. Min Act: -0.1700

Data Index: 1499980 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7926. Min Act: -0.1700

Data Index: 849203 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7753. Min Act: -0.1700

Data Index: 542836 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7652. Min Act: -0.1700

Data Index: 1504485 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7898. Min Act: -0.1700

Data Index: 773738 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7880. Min Act: -0.1700

Data Index: 885056 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7662. Min Act: -0.1700

Data Index: 296780 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7633. Min Act: -0.1700

Data Index: 720897 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7683. Min Act: -0.1700

Data Index: 1597617 (Python Code)

Max Activating Token Index: 625

Text #12

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7561. Min Act: -0.1700

Data Index: 865368 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7623. Min Act: -0.1700

Data Index: 1203729 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7457. Min Act: -0.1700

Data Index: 1433847 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7384. Min Act: -0.1700

Data Index: 1371123 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7380. Min Act: -0.1700

Data Index: 586170 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7314. Min Act: -0.1700

Data Index: 1321788 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7311. Min Act: -0.1700

Data Index: 1193329 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 2.9943. Min Range: -2.9943

Max Act: 2.7274. Min Act: -0.1700

Data Index: 879659 (C4 (Web Text))

Max Activating Token Index: 589