Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 76 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6780. Min Act: -0.1700
Data Index: 726954 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6780. Min Act: -0.1700
Data Index: 1545955 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6780. Min Act: -0.1700
Data Index: 1611774 (Python Code)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6619. Min Act: -0.1700
Data Index: 1392777 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6619. Min Act: -0.1700
Data Index: 1426227 (Python Code)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1113398 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6298. Min Act: -0.1699
Data Index: 1607685 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6459. Min Act: -0.1700
Data Index: 1408854 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6459. Min Act: -0.1700
Data Index: 1653746 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1377186 (Python Code)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1635098 (Python Code)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6138. Min Act: -0.1700
Data Index: 1595400 (Python Code)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1547001 (Python Code)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.5977. Min Act: -0.1700
Data Index: 1431865 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6138. Min Act: -0.1700
Data Index: 1509798 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6138. Min Act: -0.1700
Data Index: 1624218 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6138. Min Act: -0.1700
Data Index: 1442455 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6138. Min Act: -0.1700
Data Index: 1380334 (Python Code)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1517939 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6780. Min Range: -2.6780
Max Act: 2.6138. Min Act: -0.1700
Data Index: 980743 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19