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

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

Neuron 32 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: 3.1943. Min Range: -3.1943

Max Act: 3.1909. Min Act: -0.1700

Data Index: 1063018 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.1943. Min Act: -0.1700

Data Index: 283481 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.1207. Min Act: -0.1700

Data Index: 1281090 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.1487. Min Act: -0.1699

Data Index: 1297531 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.1142. Min Act: -0.1700

Data Index: 1073390 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.1164. Min Act: -0.1700

Data Index: 299202 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0773. Min Act: -0.1700

Data Index: 727591 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0658. Min Act: -0.1700

Data Index: 1262234 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0774. Min Act: -0.1700

Data Index: 131660 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0807. Min Act: -0.1700

Data Index: 741002 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0668. Min Act: -0.1700

Data Index: 825531 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0442. Min Act: -0.1700

Data Index: 471548 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0327. Min Act: -0.1700

Data Index: 1419707 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0219. Min Act: -0.1700

Data Index: 487704 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0103. Min Act: -0.1700

Data Index: 1053990 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0278. Min Act: -0.1700

Data Index: 852548 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0285. Min Act: -0.1700

Data Index: 1527361 (Python Code)

Max Activating Token Index: 527

Text #17

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0163. Min Act: -0.1700

Data Index: 1505605 (Python Code)

Max Activating Token Index: 477

Text #18

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0023. Min Act: -0.1700

Data Index: 1242336 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 3.1943. Min Range: -3.1943

Max Act: 3.0175. Min Act: -0.1700

Data Index: 244213 (C4 (Web Text))

Max Activating Token Index: 936