Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1989 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.2259. Min Act: -0.1700
Data Index: 1569654 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.1634. Min Act: -0.1700
Data Index: 436731 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.1009. Min Act: -0.1700
Data Index: 197212 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0696. Min Act: -0.1700
Data Index: 1012637 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.1009. Min Act: -0.1700
Data Index: 409087 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.1009. Min Act: -0.1700
Data Index: 1439360 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.1321. Min Act: -0.1700
Data Index: 1578287 (Python Code)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0696. Min Act: -0.1700
Data Index: 1473060 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.1009. Min Act: -0.1700
Data Index: 20944 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.1009. Min Act: -0.1700
Data Index: 762617 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0696. Min Act: -0.1700
Data Index: 5109 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0383. Min Act: -0.1700
Data Index: 1500677 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0383. Min Act: -0.1700
Data Index: 1649210 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0383. Min Act: -0.1700
Data Index: 1619101 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0071. Min Act: -0.1700
Data Index: 18720 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0071. Min Act: -0.1700
Data Index: 484529 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2259. Min Range: -4.2259
Max Act: 4.0071. Min Act: -0.1700
Data Index: 1286730 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2259. Min Range: -4.2259
Max Act: 3.9758. Min Act: -0.1700
Data Index: 316376 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2259. Min Range: -4.2259
Max Act: 3.9758. Min Act: -0.1700
Data Index: 1144930 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2259. Min Range: -4.2259
Max Act: 3.9758. Min Act: -0.1700
Data Index: 814753 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19