Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2088 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.3611. Min Act: -0.1700
Data Index: 2683691 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.2986. Min Act: -0.1700
Data Index: 3552613 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.2361. Min Act: -0.1700
Data Index: 1352838 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.1424. Min Act: -0.1700
Data Index: 1130205 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.1111. Min Act: -0.1700
Data Index: 6100791 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.1111. Min Act: -0.1700
Data Index: 8202964 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.0486. Min Act: -0.1700
Data Index: 3660148 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.0486. Min Act: -0.1700
Data Index: 681183 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3611. Min Range: -6.3611
Max Act: 6.0174. Min Act: -0.1700
Data Index: 877665 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9861. Min Act: -0.1700
Data Index: 1261156 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9861. Min Act: -0.1700
Data Index: 299621 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9549. Min Act: -0.1700
Data Index: 6177438 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9861. Min Act: -0.1700
Data Index: 1786619 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9549. Min Act: -0.1700
Data Index: 2656291 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9549. Min Act: -0.1700
Data Index: 6164299 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9861. Min Act: -0.1700
Data Index: 2637694 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9549. Min Act: -0.1700
Data Index: 7569493 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9549. Min Act: -0.1700
Data Index: 1543420 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.8924. Min Act: -0.1700
Data Index: 374709 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3611. Min Range: -6.3611
Max Act: 5.9236. Min Act: -0.1700
Data Index: 4490189 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19