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

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

Neuron 798 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: 3.8337. Min Range: -3.8337

Max Act: 3.8337. Min Act: -0.1700

Data Index: 875986 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.7100. Min Act: -0.1699

Data Index: 211876 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.6552. Min Act: -0.1700

Data Index: 263377 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.6463. Min Act: -0.1700

Data Index: 1110519 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.6069. Min Act: -0.1700

Data Index: 209523 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.6157. Min Act: -0.1700

Data Index: 56056 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5990. Min Act: -0.1700

Data Index: 704481 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5502. Min Act: -0.1700

Data Index: 1117952 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5354. Min Act: -0.1700

Data Index: 1247257 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5540. Min Act: -0.1700

Data Index: 682217 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5221. Min Act: -0.1700

Data Index: 1337351 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5260. Min Act: -0.1700

Data Index: 697534 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5446. Min Act: -0.1700

Data Index: 1118433 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5158. Min Act: -0.1700

Data Index: 100234 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5425. Min Act: -0.1700

Data Index: 458920 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5044. Min Act: -0.1700

Data Index: 1313780 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.5001. Min Act: -0.1700

Data Index: 905520 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.4792. Min Act: -0.1700

Data Index: 151945 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.4787. Min Act: -0.1700

Data Index: 1204999 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 3.8337. Min Range: -3.8337

Max Act: 3.4880. Min Act: -0.1700

Data Index: 302446 (C4 (Web Text))

Max Activating Token Index: 350