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

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

Neuron 1063 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: 4.1241. Min Range: -4.1241

Max Act: 4.1241. Min Act: -0.1700

Data Index: 478547 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 4.1241. Min Range: -4.1241

Max Act: 4.0373. Min Act: -0.1700

Data Index: 284343 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 4.1241. Min Range: -4.1241

Max Act: 4.0359. Min Act: -0.1700

Data Index: 47654 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 4.1241. Min Range: -4.1241

Max Act: 4.0285. Min Act: -0.1700

Data Index: 41708 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9893. Min Act: -0.1700

Data Index: 595259 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 4.1241. Min Range: -4.1241

Max Act: 4.0100. Min Act: -0.1700

Data Index: 179749 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 4.1241. Min Range: -4.1241

Max Act: 4.0066. Min Act: -0.1700

Data Index: 557558 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9737. Min Act: -0.1700

Data Index: 65163 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9900. Min Act: -0.1700

Data Index: 984540 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9758. Min Act: -0.1700

Data Index: 951538 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9534. Min Act: -0.1700

Data Index: 241945 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9383. Min Act: -0.1700

Data Index: 901151 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9329. Min Act: -0.1700

Data Index: 754634 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9397. Min Act: -0.1700

Data Index: 710082 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9399. Min Act: -0.1700

Data Index: 686479 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9441. Min Act: -0.1700

Data Index: 1205715 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9145. Min Act: -0.1700

Data Index: 826756 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9242. Min Act: -0.1700

Data Index: 1157127 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9261. Min Act: -0.1700

Data Index: 311013 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 4.1241. Min Range: -4.1241

Max Act: 3.9165. Min Act: -0.1700

Data Index: 360083 (C4 (Web Text))

Max Activating Token Index: 359