Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.8938. Min Act: -0.1700
Data Index: 6602058 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.7688. Min Act: -0.1700
Data Index: 7582714 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.7063. Min Act: -0.1700
Data Index: 1963851 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.6438. Min Act: -0.1700
Data Index: 4569669 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.5813. Min Act: -0.1700
Data Index: 2909717 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.5188. Min Act: -0.1700
Data Index: 819978 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.3938. Min Act: -0.1700
Data Index: 7680750 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.2688. Min Act: -0.1700
Data Index: 242100 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.2688. Min Act: -0.1700
Data Index: 3231526 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.2063. Min Act: -0.1700
Data Index: 8643949 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.2063. Min Act: -0.1700
Data Index: 6972791 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.2688. Min Act: -0.1700
Data Index: 1986214 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 1986215 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 4514122 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 7111173 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.1438. Min Act: -0.1700
Data Index: 633579 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.0501. Min Act: -0.1700
Data Index: 3304179 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.0501. Min Act: -0.1700
Data Index: 3369001 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8938. Min Range: -8.8938
Max Act: 8.0188. Min Act: -0.1700
Data Index: 4337036 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8938. Min Range: -8.8938
Max Act: 7.9876. Min Act: -0.1700
Data Index: 6418188 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19