Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6337 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.6753. Min Act: -0.1700
Data Index: 1696479 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.6753. Min Act: -0.1700
Data Index: 1589151 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.6128. Min Act: -0.1700
Data Index: 3245072 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.6128. Min Act: -0.1700
Data Index: 127222 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.4253. Min Act: -0.1700
Data Index: 1922480 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.3940. Min Act: -0.1700
Data Index: 1294849 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.3628. Min Act: -0.1700
Data Index: 6688814 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.3628. Min Act: -0.1700
Data Index: 285855 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.3003. Min Act: -0.1700
Data Index: 5096363 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2690. Min Act: -0.1700
Data Index: 7205946 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2690. Min Act: -0.1700
Data Index: 2359091 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2378. Min Act: -0.1700
Data Index: 3104891 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2378. Min Act: -0.1700
Data Index: 5985699 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2378. Min Act: -0.1700
Data Index: 5320450 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2065. Min Act: -0.1700
Data Index: 7400452 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2065. Min Act: -0.1700
Data Index: 4326063 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.2065. Min Act: -0.1700
Data Index: 6376448 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.1753. Min Act: -0.1700
Data Index: 5859828 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.1753. Min Act: -0.1700
Data Index: 4684582 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6753. Min Range: -7.6753
Max Act: 7.1753. Min Act: -0.1700
Data Index: 4596776 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19