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

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

Neuron 644 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: 3.5942. Min Range: -3.5942

Max Act: 3.5942. Min Act: -0.1700

Data Index: 1102173 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.5398. Min Act: -0.1700

Data Index: 1309745 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.5157. Min Act: -0.1700

Data Index: 1138285 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.5030. Min Act: -0.1700

Data Index: 163692 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4919. Min Act: -0.1700

Data Index: 899493 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4666. Min Act: -0.1700

Data Index: 781239 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4406. Min Act: -0.1700

Data Index: 216487 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4494. Min Act: -0.1700

Data Index: 1280277 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4512. Min Act: -0.1700

Data Index: 953561 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4707. Min Act: -0.1700

Data Index: 722206 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4125. Min Act: -0.1700

Data Index: 595386 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4407. Min Act: -0.1700

Data Index: 1265327 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4268. Min Act: -0.1700

Data Index: 691693 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4531. Min Act: -0.1700

Data Index: 154270 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4192. Min Act: -0.1700

Data Index: 54542 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4135. Min Act: -0.1700

Data Index: 525078 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4277. Min Act: -0.1700

Data Index: 665341 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4028. Min Act: -0.1700

Data Index: 1227180 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.3994. Min Act: -0.1700

Data Index: 1233691 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 3.5942. Min Range: -3.5942

Max Act: 3.4104. Min Act: -0.1700

Data Index: 451301 (C4 (Web Text))

Max Activating Token Index: 435