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

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

Neuron 222 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: 3.7183. Min Range: -3.7183

Max Act: 3.7183. Min Act: -0.1700

Data Index: 1606211 (Python Code)

Max Activating Token Index: 400

Text #1

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.7077. Min Act: -0.1700

Data Index: 1601935 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.7015. Min Act: -0.1700

Data Index: 1548670 (Python Code)

Max Activating Token Index: 451

Text #3

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6841. Min Act: -0.1700

Data Index: 1648892 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6952. Min Act: -0.1700

Data Index: 1587470 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1596026 (Python Code)

Max Activating Token Index: 173

Text #6

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6720. Min Act: -0.1700

Data Index: 1422586 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6453. Min Act: -0.1700

Data Index: 1647859 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6542. Min Act: -0.1700

Data Index: 1435142 (Python Code)

Max Activating Token Index: 862

Text #9

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6711. Min Act: -0.1700

Data Index: 1414264 (Python Code)

Max Activating Token Index: 518

Text #10

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6206. Min Act: -0.1700

Data Index: 1400672 (Python Code)

Max Activating Token Index: 442

Text #11

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6285. Min Act: -0.1700

Data Index: 1420373 (Python Code)

Max Activating Token Index: 986

Text #12

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1482401 (Python Code)

Max Activating Token Index: 279

Text #13

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6186. Min Act: -0.1700

Data Index: 1413403 (Python Code)

Max Activating Token Index: 92

Text #14

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6249. Min Act: -0.1700

Data Index: 1520119 (Python Code)

Max Activating Token Index: 304

Text #15

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1458011 (Python Code)

Max Activating Token Index: 886

Text #16

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6200. Min Act: -0.1700

Data Index: 1406151 (Python Code)

Max Activating Token Index: 420

Text #17

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6133. Min Act: -0.1700

Data Index: 1514174 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6276. Min Act: -0.1700

Data Index: 1389850 (Python Code)

Max Activating Token Index: 400

Text #19

Max Range: 3.7183. Min Range: -3.7183

Max Act: 3.6105. Min Act: -0.1700

Data Index: 1428087 (Python Code)

Max Activating Token Index: 938