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

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

Neuron 215 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: 3.7893. Min Range: -3.7893

Max Act: 3.7893. Min Act: -0.1700

Data Index: 1441499 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.7236. Min Act: -0.1700

Data Index: 1600278 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.6348. Min Act: -0.1700

Data Index: 1481188 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.6149. Min Act: -0.1700

Data Index: 1546719 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5853. Min Act: -0.1700

Data Index: 1477271 (Python Code)

Max Activating Token Index: 842

Text #5

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.5663. Min Act: -0.1700

Data Index: 1564155 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3834. Min Act: -0.1700

Data Index: 1623924 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4208. Min Act: -0.1700

Data Index: 1623271 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4405. Min Act: -0.1700

Data Index: 1570824 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4110. Min Act: -0.1700

Data Index: 1474973 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4287. Min Act: -0.1700

Data Index: 1648565 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.4125. Min Act: -0.1700

Data Index: 1375466 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3997. Min Act: -0.1700

Data Index: 1549874 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3922. Min Act: -0.1700

Data Index: 1392481 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3823. Min Act: -0.1700

Data Index: 1423770 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3822. Min Act: -0.1700

Data Index: 1505998 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3474. Min Act: -0.1700

Data Index: 1554541 (Python Code)

Max Activating Token Index: 818

Text #17

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3808. Min Act: -0.1700

Data Index: 1366374 (Python Code)

Max Activating Token Index: 228

Text #18

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3400. Min Act: -0.1700

Data Index: 1436289 (Python Code)

Max Activating Token Index: 308

Text #19

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3418. Min Act: -0.1700

Data Index: 1456666 (Python Code)

Max Activating Token Index: 638