Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 696 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.6749. Min Act: -0.1700
Data Index: 1177230 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.7061. Min Act: -0.1700
Data Index: 1441810 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.6436. Min Act: -0.1700
Data Index: 733848 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.6749. Min Act: -0.1700
Data Index: 995894 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.5499. Min Act: -0.1700
Data Index: 910435 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.6124. Min Act: -0.1700
Data Index: 631533 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.5499. Min Act: -0.1700
Data Index: 1358866 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.5186. Min Act: -0.1700
Data Index: 413099 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.6124. Min Act: -0.1700
Data Index: 639352 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4874. Min Act: -0.1700
Data Index: 1171750 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.6124. Min Act: -0.1700
Data Index: 884712 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.5811. Min Act: -0.1700
Data Index: 480411 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.5186. Min Act: -0.1700
Data Index: 931940 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4874. Min Act: -0.1700
Data Index: 650755 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4561. Min Act: -0.1700
Data Index: 669787 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4561. Min Act: -0.1700
Data Index: 1501761 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4561. Min Act: -0.1700
Data Index: 1403914 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4874. Min Act: -0.1700
Data Index: 1620482 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4561. Min Act: -0.1700
Data Index: 267531 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7061. Min Range: -4.7061
Max Act: 4.4561. Min Act: -0.1700
Data Index: 418888 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19