Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3681 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.8946. Min Act: -0.1700
Data Index: 4950714 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.8321. Min Act: -0.1700
Data Index: 5309883 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.8321. Min Act: -0.1700
Data Index: 2080758 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.8321. Min Act: -0.1700
Data Index: 1997545 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.8008. Min Act: -0.1700
Data Index: 8427627 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.7696. Min Act: -0.1700
Data Index: 4890070 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.7383. Min Act: -0.1700
Data Index: 7389625 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.7071. Min Act: -0.1700
Data Index: 2983740 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.7071. Min Act: -0.1700
Data Index: 693355 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6446. Min Act: -0.1700
Data Index: 2627834 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6446. Min Act: -0.1700
Data Index: 818085 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.7071. Min Act: -0.1700
Data Index: 257573 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6446. Min Act: -0.1700
Data Index: 5979976 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6758. Min Act: -0.1700
Data Index: 5545595 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6446. Min Act: -0.1700
Data Index: 3668116 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6133. Min Act: -0.1700
Data Index: 2787454 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6133. Min Act: -0.1700
Data Index: 6945129 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6133. Min Act: -0.1700
Data Index: 3434838 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6133. Min Act: -0.1700
Data Index: 3475907 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8946. Min Range: -5.8946
Max Act: 5.6133. Min Act: -0.1700
Data Index: 2415412 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19