Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.8846. Min Act: -0.1700
Data Index: 884446 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.7909. Min Act: -0.1700
Data Index: 7859859 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.7909. Min Act: -0.1700
Data Index: 1521069 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.7284. Min Act: -0.1700
Data Index: 8558353 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.6659. Min Act: -0.1700
Data Index: 7859865 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.6971. Min Act: -0.1700
Data Index: 3329082 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.5721. Min Act: -0.1700
Data Index: 8118296 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.5721. Min Act: -0.1700
Data Index: 3805086 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.5409. Min Act: -0.1700
Data Index: 6823770 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.5096. Min Act: -0.1699
Data Index: 6803553 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.4784. Min Act: -0.1700
Data Index: 7653001 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.4159. Min Act: -0.1700
Data Index: 6996929 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.4159. Min Act: -0.1700
Data Index: 762099 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 459817 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 2402862 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 6249562 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 7721790 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3846. Min Act: -0.1700
Data Index: 1034953 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.3534. Min Act: -0.1700
Data Index: 4497756 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8846. Min Range: -6.8846
Max Act: 6.2909. Min Act: -0.1700
Data Index: 6138330 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19