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

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

Neuron 311 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: 3.3939. Min Range: -3.3939

Max Act: 3.3939. Min Act: -0.1700

Data Index: 668155 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.3405. Min Act: -0.1700

Data Index: 1010845 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.3200. Min Act: -0.1700

Data Index: 844034 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2976. Min Act: -0.1700

Data Index: 1088493 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2997. Min Act: -0.1700

Data Index: 906832 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2670. Min Act: -0.1700

Data Index: 87129 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2508. Min Act: -0.1700

Data Index: 481061 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2445. Min Act: -0.1700

Data Index: 254487 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2554. Min Act: -0.1700

Data Index: 989969 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2386. Min Act: -0.1700

Data Index: 785850 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2436. Min Act: -0.1700

Data Index: 823628 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2340. Min Act: -0.1700

Data Index: 693377 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2388. Min Act: -0.1700

Data Index: 633660 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.2164. Min Act: -0.1700

Data Index: 539181 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.1821. Min Act: -0.1700

Data Index: 464908 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.1708. Min Act: -0.1700

Data Index: 154793 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.1480. Min Act: -0.1700

Data Index: 1264622 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.1116. Min Act: -0.1700

Data Index: 1007799 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.1316. Min Act: -0.1700

Data Index: 752014 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 3.3939. Min Range: -3.3939

Max Act: 3.1255. Min Act: -0.1700

Data Index: 194873 (C4 (Web Text))

Max Activating Token Index: 579