Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2758. Min Range: -7.2758
Max Act: 7.2758. Min Act: -0.1700
Data Index: 5838695 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2758. Min Range: -7.2758
Max Act: 7.2133. Min Act: -0.1700
Data Index: 2556465 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2758. Min Range: -7.2758
Max Act: 7.2133. Min Act: -0.1700
Data Index: 8102753 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2758. Min Range: -7.2758
Max Act: 7.0883. Min Act: -0.1700
Data Index: 6232027 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2758. Min Range: -7.2758
Max Act: 7.0258. Min Act: -0.1700
Data Index: 8568099 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.9633. Min Act: -0.1700
Data Index: 2289277 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.9321. Min Act: -0.1700
Data Index: 1679978 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.9008. Min Act: -0.1700
Data Index: 4652755 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.8696. Min Act: -0.1700
Data Index: 3772832 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.9008. Min Act: -0.1700
Data Index: 3183488 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.9008. Min Act: -0.1700
Data Index: 8647918 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.9008. Min Act: -0.1700
Data Index: 2472018 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.8696. Min Act: -0.1700
Data Index: 3981229 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.8696. Min Act: -0.1700
Data Index: 4182770 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.7758. Min Act: -0.1700
Data Index: 6133181 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2136227 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.6821. Min Act: -0.1700
Data Index: 4238466 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.6821. Min Act: -0.1700
Data Index: 641023 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.6508. Min Act: -0.1700
Data Index: 4822954 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2758. Min Range: -7.2758
Max Act: 6.6508. Min Act: -0.1700
Data Index: 1454950 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19