Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4734. Min Range: -7.4734
Max Act: 7.4734. Min Act: -0.1700
Data Index: 6295754 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4734. Min Range: -7.4734
Max Act: 7.0359. Min Act: -0.1700
Data Index: 1369672 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4734. Min Range: -7.4734
Max Act: 7.0046. Min Act: -0.1700
Data Index: 23635 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4734. Min Range: -7.4734
Max Act: 7.0046. Min Act: -0.1700
Data Index: 62944 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.9421. Min Act: -0.1700
Data Index: 6467832 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.9109. Min Act: -0.1700
Data Index: 7738378 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.8484. Min Act: -0.1700
Data Index: 2791796 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.8171. Min Act: -0.1700
Data Index: 4692236 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7859. Min Act: -0.1700
Data Index: 473269 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7859. Min Act: -0.1700
Data Index: 7448061 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7859. Min Act: -0.1700
Data Index: 2847722 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7859. Min Act: -0.1700
Data Index: 2679874 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7859. Min Act: -0.1700
Data Index: 1486729 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7546. Min Act: -0.1700
Data Index: 4353778 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7546. Min Act: -0.1700
Data Index: 3703375 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7234. Min Act: -0.1700
Data Index: 7011497 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7234. Min Act: -0.1700
Data Index: 8247352 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7546. Min Act: -0.1700
Data Index: 463314 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.7234. Min Act: -0.1700
Data Index: 5469313 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4734. Min Range: -7.4734
Max Act: 6.6921. Min Act: -0.1700
Data Index: 7187865 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19