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

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

Neuron 1444 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: 3.9155. Min Range: -3.9155

Max Act: 3.9155. Min Act: -0.1700

Data Index: 1227987 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.8362. Min Act: -0.1700

Data Index: 536153 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.8172. Min Act: -0.1700

Data Index: 71956 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.8154. Min Act: -0.1700

Data Index: 108467 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.8165. Min Act: -0.1700

Data Index: 808442 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.8062. Min Act: -0.1700

Data Index: 604450 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7915. Min Act: -0.1700

Data Index: 1062190 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7853. Min Act: -0.1700

Data Index: 1214063 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7682. Min Act: -0.1700

Data Index: 415508 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7681. Min Act: -0.1700

Data Index: 404287 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7507. Min Act: -0.1700

Data Index: 1051870 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7543. Min Act: -0.1700

Data Index: 1343512 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7335. Min Act: -0.1700

Data Index: 967523 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7331. Min Act: -0.1700

Data Index: 426531 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7500. Min Act: -0.1700

Data Index: 1243737 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7350. Min Act: -0.1700

Data Index: 1229984 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7170. Min Act: -0.1700

Data Index: 1157584 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7269. Min Act: -0.1700

Data Index: 487991 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7160. Min Act: -0.1700

Data Index: 617582 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 3.9155. Min Range: -3.9155

Max Act: 3.7118. Min Act: -0.1700

Data Index: 1188724 (C4 (Web Text))

Max Activating Token Index: 436