Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2039 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5909. Min Range: -6.5909
Max Act: 6.5909. Min Act: -0.1700
Data Index: 8640154 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5909. Min Range: -6.5909
Max Act: 6.1846. Min Act: -0.1700
Data Index: 5225300 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5909. Min Range: -6.5909
Max Act: 6.1221. Min Act: -0.1700
Data Index: 5588315 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5909. Min Range: -6.5909
Max Act: 6.0909. Min Act: -0.1700
Data Index: 6237839 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5909. Min Range: -6.5909
Max Act: 6.0909. Min Act: -0.1700
Data Index: 2044362 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5909. Min Range: -6.5909
Max Act: 6.0596. Min Act: -0.1700
Data Index: 6150979 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5909. Min Range: -6.5909
Max Act: 6.0284. Min Act: -0.1700
Data Index: 2044364 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.9971. Min Act: -0.1700
Data Index: 6746258 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.9659. Min Act: -0.1700
Data Index: 4873064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.9034. Min Act: -0.1700
Data Index: 5063092 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.9034. Min Act: -0.1700
Data Index: 72562 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.8721. Min Act: -0.1700
Data Index: 975246 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.8409. Min Act: -0.1700
Data Index: 7862523 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.8096. Min Act: -0.1700
Data Index: 2437662 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.7784. Min Act: -0.1700
Data Index: 8561854 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.7471. Min Act: -0.1700
Data Index: 3697206 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.7471. Min Act: -0.1700
Data Index: 5010787 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.7471. Min Act: -0.1700
Data Index: 285053 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.7471. Min Act: -0.1700
Data Index: 6507599 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5909. Min Range: -6.5909
Max Act: 5.7159. Min Act: -0.1700
Data Index: 1914176 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19