Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1902 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.6734. Min Act: -0.1700
Data Index: 2815533 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.5484. Min Act: -0.1700
Data Index: 5966887 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.5484. Min Act: -0.1700
Data Index: 996617 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.5171. Min Act: -0.1700
Data Index: 3877975 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.4234. Min Act: -0.1700
Data Index: 1962550 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.3921. Min Act: -0.1700
Data Index: 4826268 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.3921. Min Act: -0.1700
Data Index: 2741942 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.3921. Min Act: -0.1700
Data Index: 5838566 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.3609. Min Act: -0.1700
Data Index: 6111147 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.3296. Min Act: -0.1700
Data Index: 1161521 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2984. Min Act: -0.1700
Data Index: 996608 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.3296. Min Act: -0.1700
Data Index: 1163009 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.3296. Min Act: -0.1700
Data Index: 7843442 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2984. Min Act: -0.1700
Data Index: 7191178 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2984. Min Act: -0.1700
Data Index: 2622103 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2359. Min Act: -0.1700
Data Index: 2982248 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2671. Min Act: -0.1700
Data Index: 8184797 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2671. Min Act: -0.1700
Data Index: 8100632 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2671. Min Act: -0.1700
Data Index: 1165850 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6734. Min Range: -6.6734
Max Act: 6.2359. Min Act: -0.1700
Data Index: 6431275 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19