Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5258 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.7920. Min Act: -0.1700
Data Index: 358922 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.5729. Min Act: -0.1693
Data Index: 7868707 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.5729. Min Act: -0.1700
Data Index: 1985550 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3846301 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3232837 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4790. Min Act: -0.1700
Data Index: 8823930 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4476. Min Act: -0.1698
Data Index: 7122669 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4790. Min Act: -0.1698
Data Index: 1660714 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4790. Min Act: -0.1700
Data Index: 1518209 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4476. Min Act: -0.1700
Data Index: 3564036 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4476. Min Act: -0.1700
Data Index: 8031558 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4790. Min Act: -0.1700
Data Index: 7994045 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4790. Min Act: -0.1700
Data Index: 914608 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4790. Min Act: -0.1700
Data Index: 247675 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4790. Min Act: -0.1700
Data Index: 7865561 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4476. Min Act: -0.1700
Data Index: 4567669 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4476. Min Act: -0.1700
Data Index: 2910696 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4163. Min Act: -0.1697
Data Index: 3749497 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4476. Min Act: -0.1700
Data Index: 1470637 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7920. Min Range: -3.7920
Max Act: 3.4476. Min Act: -0.1699
Data Index: 3865242 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19