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

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

Neuron 1979 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: 3.4287. Min Range: -3.4287

Max Act: 3.4287. Min Act: -0.1699

Data Index: 538158 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.4139. Min Act: -0.1700

Data Index: 86719 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.4050. Min Act: -0.1700

Data Index: 452062 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.3524. Min Act: -0.1700

Data Index: 502504 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.3456. Min Act: -0.1700

Data Index: 629234 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.3346. Min Act: -0.1700

Data Index: 152133 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.3173. Min Act: -0.1700

Data Index: 876825 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2979. Min Act: -0.1700

Data Index: 780871 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2785. Min Act: -0.1700

Data Index: 1101230 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2806. Min Act: -0.1700

Data Index: 422883 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2551. Min Act: -0.1700

Data Index: 628625 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2489. Min Act: -0.1700

Data Index: 843463 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2344. Min Act: -0.1700

Data Index: 506635 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2205. Min Act: -0.1700

Data Index: 477164 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2186. Min Act: -0.1700

Data Index: 510085 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2361. Min Act: -0.1700

Data Index: 1107522 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2128. Min Act: -0.1700

Data Index: 76507 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2164. Min Act: -0.1700

Data Index: 60561 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2085. Min Act: -0.1700

Data Index: 1099862 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 3.4287. Min Range: -3.4287

Max Act: 3.2296. Min Act: -0.1700

Data Index: 311849 (C4 (Web Text))

Max Activating Token Index: 994