Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.6999. Min Act: -0.1700
Data Index: 4907623 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.2624. Min Act: -0.1700
Data Index: 361904 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.2312. Min Act: -0.1700
Data Index: 7073348 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.1999. Min Act: -0.1700
Data Index: 4057836 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.2312. Min Act: -0.1700
Data Index: 2317149 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.1687. Min Act: -0.1700
Data Index: 179836 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.1062. Min Act: -0.1700
Data Index: 7655714 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.0749. Min Act: -0.1700
Data Index: 6200086 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.0749. Min Act: -0.1700
Data Index: 8772011 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.0437. Min Act: -0.1700
Data Index: 2240389 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.9812. Min Act: -0.1700
Data Index: 3275664 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.9812. Min Act: -0.1700
Data Index: 7166760 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.9812. Min Act: -0.1700
Data Index: 504780 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6999. Min Range: -6.6999
Max Act: 6.0124. Min Act: -0.1700
Data Index: 1991008 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.9499. Min Act: -0.1700
Data Index: 6358801 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.9499. Min Act: -0.1700
Data Index: 8451200 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.9499. Min Act: -0.1700
Data Index: 6301139 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.8874. Min Act: -0.1700
Data Index: 502964 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.8874. Min Act: -0.1700
Data Index: 7502775 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6999. Min Range: -6.6999
Max Act: 5.9187. Min Act: -0.1700
Data Index: 2958747 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19