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

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

Neuron 121 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: 3.3133. Min Range: -3.3133

Max Act: 3.3058. Min Act: -0.1700

Data Index: 529489 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.3043. Min Act: -0.1700

Data Index: 611116 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.3133. Min Act: -0.1700

Data Index: 552559 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2913. Min Act: -0.1700

Data Index: 307661 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2332. Min Act: -0.1700

Data Index: 1501114 (Python Code)

Max Activating Token Index: 415

Text #5

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2198. Min Act: -0.1700

Data Index: 172564 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2369. Min Act: -0.1700

Data Index: 1109731 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2197. Min Act: -0.1700

Data Index: 962036 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2254. Min Act: -0.1700

Data Index: 254977 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2187. Min Act: -0.1700

Data Index: 851507 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2220. Min Act: -0.1700

Data Index: 940891 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2118. Min Act: -0.1700

Data Index: 589646 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2109. Min Act: -0.1700

Data Index: 1230446 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.2117. Min Act: -0.1700

Data Index: 371942 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1913. Min Act: -0.1700

Data Index: 31427 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1765. Min Act: -0.1700

Data Index: 1229150 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1923. Min Act: -0.1700

Data Index: 1316765 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1909. Min Act: -0.1700

Data Index: 928738 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1950. Min Act: -0.1700

Data Index: 422024 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 3.3133. Min Range: -3.3133

Max Act: 3.1659. Min Act: -0.1700

Data Index: 24200 (C4 (Web Text))

Max Activating Token Index: 360