Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.5508. Min Act: -0.1700
Data Index: 1863565 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.2696. Min Act: -0.1700
Data Index: 551723 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.1758. Min Act: -0.1700
Data Index: 2554033 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.1758. Min Act: -0.1700
Data Index: 8725767 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.1446. Min Act: -0.1700
Data Index: 8312869 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.1758. Min Act: -0.1700
Data Index: 3518752 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.1446. Min Act: -0.1700
Data Index: 408331 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.1133. Min Act: -0.1700
Data Index: 203615 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.0821. Min Act: -0.1700
Data Index: 5481042 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.0508. Min Act: -0.1700
Data Index: 1986464 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5508. Min Range: -7.5508
Max Act: 7.0196. Min Act: -0.1700
Data Index: 8199608 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9883. Min Act: -0.1700
Data Index: 2574672 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9883. Min Act: -0.1700
Data Index: 8067895 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9883. Min Act: -0.1700
Data Index: 6303344 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9571. Min Act: -0.1700
Data Index: 197910 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9258. Min Act: -0.1700
Data Index: 6283021 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9571. Min Act: -0.1700
Data Index: 7610555 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9571. Min Act: -0.1700
Data Index: 5613438 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9258. Min Act: -0.1700
Data Index: 2384449 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5508. Min Range: -7.5508
Max Act: 6.9258. Min Act: -0.1700
Data Index: 5897975 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19