Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 699 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3956. Min Act: -0.1700
Data Index: 1218000 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3956. Min Act: -0.1700
Data Index: 1487731 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3956. Min Act: -0.1700
Data Index: 4132760 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3956. Min Act: -0.1700
Data Index: 7088592 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3644. Min Act: -0.1700
Data Index: 5610359 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3644. Min Act: -0.1700
Data Index: 339081 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3019. Min Act: -0.1700
Data Index: 5629013 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3019. Min Act: -0.1700
Data Index: 8686146 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3019. Min Act: -0.1700
Data Index: 7086095 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.3331. Min Act: -0.1700
Data Index: 2937262 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.2706. Min Act: -0.1700
Data Index: 8081107 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.2081. Min Act: -0.1700
Data Index: 1677696 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.2394. Min Act: -0.1700
Data Index: 6289838 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.2081. Min Act: -0.1700
Data Index: 4077767 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.2081. Min Act: -0.1700
Data Index: 7645471 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.2081. Min Act: -0.1700
Data Index: 7274803 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.2081. Min Act: -0.1700
Data Index: 8622838 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.1769. Min Act: -0.1700
Data Index: 7628214 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.1769. Min Act: -0.1700
Data Index: 4085630 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3956. Min Range: -5.3956
Max Act: 5.1769. Min Act: -0.1700
Data Index: 7592742 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19