Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5512 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2800. Min Range: -6.2800
Max Act: 6.2800. Min Act: -0.1700
Data Index: 2194830 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.9363. Min Act: -0.1700
Data Index: 18094 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.8738. Min Act: -0.1700
Data Index: 6880464 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.8738. Min Act: -0.1700
Data Index: 3917489 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.8113. Min Act: -0.1700
Data Index: 2697116 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.8113. Min Act: -0.1700
Data Index: 2063644 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.7800. Min Act: -0.1700
Data Index: 3772412 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.7175. Min Act: -0.1700
Data Index: 5406880 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.7800. Min Act: -0.1700
Data Index: 5905953 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.7488. Min Act: -0.1700
Data Index: 7192111 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.7488. Min Act: -0.1700
Data Index: 6874046 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6863. Min Act: -0.1700
Data Index: 903959 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6863. Min Act: -0.1700
Data Index: 7781848 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6550. Min Act: -0.1700
Data Index: 6417985 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6550. Min Act: -0.1700
Data Index: 7879712 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6550. Min Act: -0.1700
Data Index: 8730965 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6238. Min Act: -0.1700
Data Index: 7240115 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6238. Min Act: -0.1700
Data Index: 5403111 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6238. Min Act: -0.1700
Data Index: 6995873 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2800. Min Range: -6.2800
Max Act: 5.6238. Min Act: -0.1700
Data Index: 4273549 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19